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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fare
    -0.07
     mis
    -0.07
     toy
    -0.07
    Ethernet
    -0.06
     vos
    -0.06
     �
    -0.06
    _back
    -0.06
     idi
    -0.06
     entender
    -0.06
     Aless
    -0.06
    POSITIVE LOGITS
     yarg
    0.07
    تظاهر
    0.07
    这片
    0.06
     soaked
    0.06
    书中
    0.06
    ၼ
    0.06
    遄
    0.06
    此举
    0.06
    Drug
    0.06
    泅
    0.06
    Act Density 0.010%

    No Known Activations