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

    Neuronpedia

    INDEX
    Explanations

    python errors/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ativní
    -0.06
    ülü
    -0.06
    _emb
    -0.06
     shedding
    -0.06
     nbr
    -0.06
    SV
    -0.06
    south
    -0.06
     Bundy
    -0.06
    襲
    -0.06
     seedu
    -0.06
    POSITIVE LOGITS
     верес
    0.07
    .Restrict
    0.07
     castle
    0.07
    aveled
    0.06
     successive
    0.06
     конце
    0.06
    urch
    0.06
     inaccessible
    0.06
     Rift
    0.06
     rigor
    0.06
    Act Density 0.012%

    No Known Activations