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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .us
    -0.06
    Result
    -0.06
    Yaw
    -0.06
    نع
    -0.06
    Seattle
    -0.06
     nối
    -0.06
    _pad
    -0.06
     battered
    -0.06
    /select
    -0.06
    (now
    -0.06
    POSITIVE LOGITS
     نويسنده
    0.08
     onFailure
    0.07
    _inter
    0.07
    mn
    0.06
     사라
    0.06
    事情
    0.06
     clo
    0.06
     <->
    0.06
     BÖL
    0.06
     περι
    0.06
    Act Density 0.004%

    No Known Activations