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

    Neuronpedia

    INDEX
    Explanations

    references to file paths or directories in a filesystem

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

    /etc/ configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.68
     ब्रेकडाउन
    -0.58
    ConstraintMaker
    -0.56
     Numerade
    -0.54
    peteer
    -0.53
     senhora
    -0.53
    granate
    -0.53
     numberWith
    -0.52
    awtextra
    -0.52
     sval
    -0.52
    POSITIVE LOGITS
     ETC
    0.62
    etc
    0.60
    ETC
    0.58
     getConfig
    0.48
     Etc
    0.47
    Etc
    0.47
     ECC
    0.46
     etc
    0.45
    <bos>
    0.44
     ETS
    0.44
    Act Density 0.004%

    No Known Activations