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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    325
    -0.07
     regulators
    -0.07
     tarz
    -0.07
    统计
    -0.06
    τής
    -0.06
     Carter
    -0.06
     brushed
    -0.06
     image
    -0.06
    Telefone
    -0.06
     outlined
    -0.06
    POSITIVE LOGITS
    ::↵↵
    0.06
     otev
    0.06
    عنوان
    0.06
    ここ
    0.06
     %}↵
    0.06
    adapt
    0.06
     Quiet
    0.06
    ]initWith
    0.06
     peanut
    0.06
    *>::
    0.06
    Act Density 0.002%

    No Known Activations