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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ś
    -0.06
     Respond
    -0.06
     Knee
    -0.06
     deformation
    -0.05
    nob
    -0.05
     alleged
    -0.05
     judgments
    -0.05
    刺
    -0.05
    otp
    -0.05
    tdown
    -0.05
    POSITIVE LOGITS
    _LOCAL
    0.08
    /****************************************************************
    0.07
    _RX
    0.06
     организма
    0.06
    _ART
    0.06
    (rhs
    0.06
     FIFA
    0.06
     multiplayer
    0.06
    (木
    0.06
    스의
    0.06
    Act Density 0.007%

    No Known Activations