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

    Neuronpedia

    INDEX
    Explanations

    Role models/examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Strings
    -0.09
    Histogram
    -0.08
     هزینه
    -0.08
     ప్రమాద
    -0.08
    Intl
    -0.08
    _oct
    -0.08
    Slack
    -0.08
     medlems
    -0.08
    Risk
    -0.08
     exorbit
    -0.08
    POSITIVE LOGITS
    榜
    0.13
     प्रेर
    0.10
     inspirational
    0.09
     obedience
    0.09
    耀
    0.09
     inspiring
    0.09
     Insp
    0.09
     пример
    0.08
     mẫu
    0.08
    励
    0.08
    Act Density 0.032%

    No Known Activations