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

    Neuronpedia

    INDEX
    Explanations

    without stops, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    subsection
    0.64
    endent
    0.61
    StringTo
    0.59
    cett
    0.59
    getHeader
    0.59
    يزة
    0.57
    ాని
    0.56
    itius
    0.56
    lcii
    0.56
    קב
    0.55
    POSITIVE LOGITS
     it
    0.86
     you
    0.85
     there
    0.82
     remember
    0.77
     avoid
    0.76
     remembering
    0.75
     they
    0.73
     它
    0.70
     phone
    0.69
     we
    0.68
    Act Density 0.000%

    No Known Activations