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

    Neuronpedia

    INDEX
    Explanations

    contrast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recursion
    -0.06
    .ListBox
    -0.06
    iew
    -0.06
    ENT
    -0.06
    tp
    -0.06
    Lady
    -0.06
    exchange
    -0.06
    308
    -0.06
     стратег
    -0.06
    .tt
    -0.06
    POSITIVE LOGITS
     batch
    0.07
     atomic
    0.06
    ，把
    0.06
     Innovative
    0.06
    WithName
    0.06
     "{\"
    0.06
     del
    0.06
    _INTEGER
    0.06
     krb
    0.06
    _UT
    0.06
    Act Density 0.097%

    No Known Activations