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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical values and symbols, particularly within code or formulaic contexts

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

    Code or data snippets with special characters

    np_acts-logits-general · gemini-2.0-flash

    code segments and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     YS
    -0.69
     KV
    -0.67
     KK
    -0.66
     MMM
    -0.63
     VDC
    -0.62
     PPS
    -0.62
     MMMM
    -0.61
     DZ
    -0.61
     DD
    -0.61
     INI
    -0.61
    POSITIVE LOGITS
    lež
    0.58
    rzu
    0.55
    vlád
    0.52
    vski
    0.50
     princesse
    0.50
    ngth
    0.50
     huellas
    0.50
    zczy
    0.49
     bapt
    0.49
    lji
    0.49
    Act Density 1.230%

    No Known Activations