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

    Neuronpedia

    INDEX
    Explanations

    amplifying, amplified, amplify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ний
    2.02
    त
    1.86
    ル
    1.84
    тура
    1.64
    ت
    1.63
    ве
    1.63
    ன்
    1.61
    вання
    1.61
    นี้
    1.55
    تان
    1.55
    POSITIVE LOGITS
    iv
    1.45
    Ре
    1.44
    iotsitewise
    1.38
    od
    1.38
     Ελλά
    1.38
     Manuscripts
    1.38
    SPRAY
    1.37
    шого
    1.34
    Са
    1.33
    sø
    1.32
    Act Density 0.284%

    No Known Activations