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

    Neuronpedia

    INDEX
    Explanations

    Code and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     работать
    -0.08
     Dia
    -0.07
    标准
    -0.07
    不到
    -0.06
     afterward
    -0.06
     jä
    -0.06
     Blvd
    -0.06
     Freud
    -0.06
    _uuid
    -0.06
    .list
    -0.06
    POSITIVE LOGITS
    詩
    0.07
     fought
    0.07
     elite
    0.07
    .beh
    0.07
    atical
    0.06
     surrender
    0.06
     후
    0.06
     Afghan
    0.06
    :none
    0.06
    .sun
    0.06
    Act Density 0.064%

    No Known Activations