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

    Neuronpedia

    INDEX
    Explanations

    relate to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appellants
    1.59
     abruptly
    1.54
     edific
    1.49
    م
    1.47
    に
    1.46
    ಳ
    1.45
     servitude
    1.41
    ই
    1.41
    ระบบ
    1.38
     aloft
    1.35
    POSITIVE LOGITS
    een
    1.29
    bill
    1.29
    ्ह
    1.27
    bild
    1.26
    am
    1.24
    $
    1.24
    effect
    1.23
    alt
    1.20
    gallon
    1.20
     arba
    1.20
    Act Density 0.052%

    No Known Activations