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

    Neuronpedia

    INDEX
    Explanations

    decisions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    innen
    0.98
    ark
    0.97
     elektrom
    0.90
    omorf
    0.88
    itaj
    0.88
    鈉
    0.84
     λα
    0.83
     ਹੈ
    0.83
     DKI
    0.81
     jedn
    0.81
    POSITIVE LOGITS
    Ге
    0.99
    {\|
    0.98
     morbid
    0.97
     अजीब
    0.96
    ю
    0.95
    ೆ
    0.94
     bruises
    0.94
    ьо
    0.94
    蒙
    0.93
    neg
    0.92
    Act Density 0.000%

    No Known Activations