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

    Neuronpedia

    INDEX
    Explanations

    financial debt, transaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.47
     wenige
    0.41
    يا
    0.40
    os
    0.39
    on
    0.37
     científ
    0.36
    كار
    0.35
    其他
    0.35
    बि
    0.35
     médicas
    0.34
    POSITIVE LOGITS
    ۰
    0.58
     can
    0.55
    the
    0.54
     the
    0.53
    ing
    0.53
     are
    0.46
    us
    0.45
    :
    0.43
    t
    0.43
    s
    0.42
    Act Density 2.437%

    No Known Activations