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

    Neuronpedia

    INDEX
    Explanations

    movement conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Begriff
    0.47
    Edad
    0.45
    Tecla
    0.45
     витами
    0.45
     форм
    0.45
    郸
    0.44
     ת
    0.44
     א
    0.43
    อม
    0.43
    ัล
    0.43
    POSITIVE LOGITS
     eligible
    0.46
     while
    0.46
     notified
    0.46
     unless
    0.43
     during
    0.43
     if
    0.42
     until
    0.42
     credited
    0.42
     or
    0.41
     matching
    0.41
    Act Density 0.056%

    No Known Activations