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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urger
    -0.08
     Raqqa
    -0.07
    -0.06
    pine
    -0.06
    _apps
    -0.06
    thumbnails
    -0.06
    /original
    -0.06
    キ
    -0.06
     ří
    -0.06
    ุ้
    -0.06
    POSITIVE LOGITS
    を作
    0.07
     detailed
    0.06
     unaware
    0.06
     Tit
    0.06
    -loving
    0.06
    ole
    0.06
     Padres
    0.06
    IOUS
    0.06
     �
    0.06
    <dynamic
    0.06
    Act Density 0.000%

    No Known Activations