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

    Neuronpedia

    INDEX
    Explanations

    workplace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    2.22
    ون
    1.82
    で
    1.70
    matic
    1.66
    punkte
    1.65
    رش
    1.64
    ার
    1.58
    א
    1.57
    го
    1.55
    ক
    1.55
    POSITIVE LOGITS
    َ
    1.99
     negeri
    1.98
    aj
    1.90
    στε
    1.83
    om
    1.80
    ut
    1.73
    utie
    1.72
    ERTS
    1.72
    螅
    1.72
     grabando
    1.66
    Act Density 0.015%

    No Known Activations