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

    Neuronpedia

    INDEX
    Explanations

    command line flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    0.80
    t
    0.67
    yı
    0.66
     of
    0.64
     cited
    0.63
    ERCISE
    0.59
    mitted
    0.59
    たちの
    0.59
     at
    0.57
     hoạch
    0.57
    POSITIVE LOGITS
    ید
    0.64
    出
    0.64
    ర్
    0.64
    ován
    0.61
    ského
    0.59
    ých
    0.57
    ä
    0.57
    ца
    0.57
    رة
    0.56
    nél
    0.56
    Act Density 0.035%

    No Known Activations