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

    Neuronpedia

    INDEX
    Explanations

    representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AUTHORIZED
    -0.06
    ');"
    -0.06
    wire
    -0.06
     το
    -0.06
     داخلی
    -0.06
     mocked
    -0.06
    ジオ
    -0.06
    答
    -0.06
     credited
    -0.06
    ，把
    -0.06
    POSITIVE LOGITS
    -pin
    0.07
    .Inst
    0.07
    -best
    0.07
     dep
    0.07
    Deployment
    0.07
    -ret
    0.07
     comparisons
    0.06
    挥
    0.06
    @email
    0.06
     repet
    0.06
    Act Density 0.002%

    No Known Activations