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

    Neuronpedia

    INDEX
    Explanations

    template

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ưa
    -0.07
    _counter
    -0.07
    肯
    -0.07
     mott
    -0.07
    ément
    -0.07
     नस
    -0.07
    available
    -0.07
    entries
    -0.07
     મુલાકાત
    -0.07
    _mutex
    -0.07
    POSITIVE LOGITS
     준
    0.09
    ereo
    0.08
     silencio
    0.08
     horizon
    0.08
     Horizon
    0.08
     Silent
    0.08
     silence
    0.08
     solitude
    0.08
     Lear
    0.08
     deprivation
    0.08
    Act Density 0.003%

    No Known Activations