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

    Neuronpedia

    INDEX
    Explanations

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ARR
    0.44
    ER
    0.41
    תוך
    0.40
    TEM
    0.40
    ビー
    0.40
    EAR
    0.40
    OR
    0.38
    4
    0.38
    АР
    0.38
    jose
    0.38
    POSITIVE LOGITS
     Part
    0.79
     parts
    0.73
     Parts
    0.71
    icularly
    0.67
    parts
    0.66
    Parts
    0.63
    ীদার
    0.63
     part
    0.62
    Part
    0.61
    iculate
    0.61
    Act Density 0.026%

    No Known Activations