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

    Neuronpedia

    INDEX
    Explanations

    research methodology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agrid
    -0.07
     emulator
    -0.06
     Kate
    -0.06
     çevres
    -0.06
    З
    -0.06
     CS
    -0.06
    .parseColor
    -0.06
     chapel
    -0.06
     网
    -0.06
     Intent
    -0.06
    POSITIVE LOGITS
    959
    0.07
     ayrıntı
    0.06
    选�
    0.06
    _ARG
    0.06
    _sold
    0.06
    astics
    0.06
    APSHOT
    0.06
    erville
    0.06
    idth
    0.06
    大全
    0.06
    Act Density 0.003%

    No Known Activations