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

    Neuronpedia

    INDEX
    Explanations

    javascript object methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rangle
    0.43
    getClassName
    0.40
     mapas
    0.40
     compare
    0.39
    TableAdapter
    0.38
     نویس
    0.38
    \}=\
    0.37
     }))
    0.37
     lulus
    0.37
     compares
    0.37
    POSITIVE LOGITS
     ಮಿ
    0.40
    楎
    0.37
    טל
    0.37
    Deb
    0.37
     painters
    0.36
    rizio
    0.36
    ribusiness
    0.36
    μών
    0.36
     stranger
    0.35
    тать
    0.35
    Act Density 0.002%

    No Known Activations