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

    Neuronpedia

    INDEX
    Explanations

    recent years or decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的时候
    0.61
    が
    0.61
    When
    0.51
    _
    0.51
    日は
    0.50
    ：
    0.50
    くて
    0.50
    до
    0.49
    時は
    0.49
    一
    0.49
    POSITIVE LOGITS
    r
    0.75
    is
    0.61
    re
    0.57
     Keine
    0.57
    rn
    0.56
     מו
    0.55
     equivoc
    0.55
    rk
    0.52
    m
    0.52
    rd
    0.52
    Act Density 0.131%

    No Known Activations