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

    Neuronpedia

    INDEX
    Explanations

    websites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...");
↵
    -0.07
    Barrier
    -0.07
    /random
    -0.07
    odia
    -0.06
     HashMap
    -0.06
    .TestTools
    -0.06
     غ
    -0.06
    .Immutable
    -0.06
    gems
    -0.06
     Destination
    -0.06
    POSITIVE LOGITS
     flexibility
    0.07
     conoc
    0.06
     plata
    0.06
     يتم
    0.06
     grazing
    0.06
     beforeSend
    0.06
     يجب
    0.06
    _TH
    0.06
     schl
    0.06
    Video
    0.06
    Act Density 0.001%

    No Known Activations