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

    Neuronpedia

    INDEX
    Explanations

    utf-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পোকামাক
    0.47
     kivy
    0.47
    overnment
    0.46
    umba
    0.44
    orems
    0.43
    erver
    0.42
    امة
    0.42
    opathie
    0.41
    ponible
    0.41
    pike
    0.41
    POSITIVE LOGITS
    ↵↵
    0.52
    T
    0.47
     Espan
    0.43
    ਮ
    0.43
    NY
    0.42
    X
    0.42
    ES
    0.41
     impecc
    0.41
     ullamco
    0.41
    V
    0.40
    Act Density 0.000%

    No Known Activations