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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swapping
    -0.07
     concaten
    -0.06
    Typography
    -0.06
    ног
    -0.06
     वन
    -0.06
    chio
    -0.06
    inç
    -0.06
    �
    -0.06
    fires
    -0.06
     đưa
    -0.06
    POSITIVE LOGITS
    、そう
    0.06
     ACK
    0.06
    رف
    0.06
     DET
    0.06
     financial
    0.06
    <select
    0.06
    بت
    0.06
     pays
    0.06
     Cardio
    0.06
     declaration
    0.06
    Act Density 0.020%

    No Known Activations