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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and claims related to semiconductor devices

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

    Numbers following claims or paragraphs

    np_acts-logits-general · gemini-2.0-flash

    itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.73
     &
    -0.67
     </
    -0.60
     /
    -0.59
     R
    -0.58
     V
    -0.56
    &
    -0.56
     @
    -0.56
    /
    -0.55
    ↵
    -0.54
    POSITIVE LOGITS
    DockStyle
    1.32
     myſelf
    1.28
    Personensuche
    1.26
     itſelf
    1.25
    TagMode
    1.24
     Majefty
    1.20
    featureID
    1.15
     CreateTagHelper
    1.15
     ſind
    1.12
     Jefus
    1.11
    Act Density 0.128%

    No Known Activations