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

    Neuronpedia

    INDEX
    Explanations

    activision, waldgrees, sipri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ır
    0.83
     provoqu
    0.77
    де
    0.73
     accueill
    0.73
     développ
    0.70
     económicas
    0.69
    ar
    0.68
     făcut
    0.67
    arati
    0.66
    ар
    0.66
    POSITIVE LOGITS
    </h2>
    0.84
    ?
    0.83
    :
    0.82
    s
    0.82
    <0x0D>
    0.81
    ;
    0.78
    _
    0.77
    t
    0.76
    !
    0.75
    MS
    0.73
    Act Density 0.000%

    No Known Activations