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

    Neuronpedia

    INDEX
    Explanations

    Common filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (::
    -0.07
    ).__
    -0.06
    -assets
    -0.06
     mult
    -0.06
    controllers
    -0.06
    -effects
    -0.06
     tep
    -0.06
    _ct
    -0.06
    .Login
    -0.06
    gorithm
    -0.06
    POSITIVE LOGITS
    .backward
    0.07
    акон
    0.06
    Venue
    0.06
     princip
    0.06
    侵
    0.06
    áct
    0.06
    setColor
    0.06
     lối
    0.06
    оці
    0.06
    δή
    0.06
    Act Density 0.044%

    No Known Activations