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

    Neuronpedia

    INDEX
    Explanations

    activation function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rápido
    0.41
     alegre
    0.40
    хой
    0.39
     hypo
    0.38
     కుటు
    0.38
     Valentin
    0.37
     Oakland
    0.37
     mismo
    0.37
     vestido
    0.37
     വ്യക്ത
    0.36
    POSITIVE LOGITS
     zrobi
    0.44
    ИА
    0.40
    sensitive
    0.40
    sensitivity
    0.40
    setData
    0.39
     sensibilities
    0.39
     стран
    0.39
    Roberts
    0.38
     sensitivity
    0.38
    敏感
    0.38
    Act Density 0.003%

    No Known Activations