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

    Neuronpedia

    INDEX
    Explanations

    promote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hardened
    -0.07
     unlawful
    -0.07
    ergency
    -0.07
    _coeffs
    -0.06
    .isConnected
    -0.06
     Δή
    -0.06
     walked
    -0.06
     rahatsız
    -0.06
     ){↵
    -0.06
    ='%
    -0.06
    POSITIVE LOGITS
     rejuven
    0.07
    xee
    0.06
     ทอง
    0.06
    を見る
    0.06
    .Throws
    0.06
    京都
    0.06
    เกษ
    0.06
     BYU
    0.06
    ENABLE
    0.06
    DSP
    0.06
    Act Density 0.014%

    No Known Activations