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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    롯
    -0.08
    ailand
    -0.07
     FINAL
    -0.06
    بیر
    -0.06
     final
    -0.06
     humorous
    -0.06
     MOTOR
    -0.06
    bsub
    -0.06
     잠
    -0.06
    最後
    -0.06
    POSITIVE LOGITS
    thane
    0.07
     Toe
    0.07
    ım
    0.07
    lys
    0.06
    onymous
    0.06
    _trait
    0.06
     lz
    0.06
    lies
    0.06
    <&
    0.06
    =Value
    0.06
    Act Density 0.075%

    No Known Activations