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

    Neuronpedia

    INDEX
    Explanations

    argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unlink
    -0.07
    vendor
    -0.07
    msg
    -0.06
     Respond
    -0.06
    島
    -0.06
     heed
    -0.06
    管理制度
    -0.06
    Expect
    -0.06
     Technology
    -0.06
    Decl
    -0.06
    POSITIVE LOGITS
     occasions
    0.07
    ㅔ
    0.07
     Belize
    0.07
    .pa
    0.07
    我们知道
    0.07
    (o
    0.07
    คง
    0.07
    ose
    0.07
    /loading
    0.07
    若您
    0.07
    Act Density 0.006%

    No Known Activations