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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Я
    1.18
    NCIA
    1.13
     وعلى
    1.10
    ている
    1.08
    मध्ये
    1.02
    ס
    1.01
     effectué
    0.98
    的所有
    0.98
    ຢູ່
    0.97
    સે
    0.96
    POSITIVE LOGITS
    ੀ
    1.25
    ed
    1.22
    יים
    1.20
    ль
    1.19
    rapolation
    1.16
    leri
    1.14
    iere
    1.12
    iola
    1.09
     Honeywell
    1.09
    oğlu
    1.09
    Act Density 0.004%

    No Known Activations