Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical specifications and parameters related to computer systems and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Bit" and architecture size

    np_acts-logits-general · gemini-2.0-flash

    32-bit and 64-bit architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.38
    +#+#
    -0.37
    뻐
    -0.34
     InputDecoration
    -0.33
    town
    -0.33
    Town
    -0.32
    uthor
    -0.31
     town
    -0.30
    Northern
    -0.30
    OneToOne
    -0.30
    POSITIVE LOGITS
    architecture
    0.82
     architectures
    0.80
     architecture
    0.79
     arquitectura
    0.71
     bit
    0.71
     Architecture
    0.69
    architect
    0.69
     ARCHITECTURE
    0.69
     architects
    0.67
     archite
    0.66
    Act Density 0.672%

    No Known Activations