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

    Neuronpedia

    INDEX
    Explanations

    placeholders and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itant
    0.63
     camp
    0.62
     heed
    0.58
     интеллектуа
    0.58
     multi
    0.57
     Camp
    0.56
     folklor
    0.55
     alive
    0.53
    [*]
    0.53
    Camp
    0.53
    POSITIVE LOGITS
    Shall
    1.08
     Shall
    1.02
    Could
    1.00
     Is
    0.98
    could
    0.95
    features
    0.95
     Could
    0.95
     могут
    0.94
    May
    0.93
    may
    0.92
    Act Density 0.491%

    No Known Activations