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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weigh
    -0.06
    Amb
    -0.06
    .io
    -0.06
     maxi
    -0.06
    ४
    -0.06
    ничес
    -0.06
    同じ
    -0.06
     Ion
    -0.06
    ussions
    -0.06
     BASE
    -0.06
    POSITIVE LOGITS
    MITTED
    0.07
    sch
    0.07
    .runner
    0.07
    ایسه
    0.07
     abol
    0.06
     japan
    0.06
     softened
    0.06
    /services
    0.06
    )NSString
    0.06
    loha
    0.06
    Act Density 0.038%

    No Known Activations