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

    Neuronpedia

    INDEX
    Explanations

    anticipating future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     වලින්
    0.43
     присутствует
    0.42
    GRP
    0.42
    秾
    0.42
     aanwezig
    0.42
     участи
    0.41
    ાદ
    0.40
    references
    0.40
     присут
    0.39
    стів
    0.39
    POSITIVE LOGITS
     Montevideo
    0.40
     Thoreau
    0.38
     devices
    0.37
     Fort
    0.36
     DEVICE
    0.35
    monospace
    0.35
     Lyon
    0.35
    懦
    0.35
     Mitch
    0.35
     mica
    0.35
    Act Density 0.001%

    No Known Activations