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

    Neuronpedia

    INDEX
    Explanations

    mix and match

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ği
    1.78
    า
    1.77
    eny
    1.70
    ח
    1.66
    сть
    1.58
    are
    1.55
    usual
    1.55
    ının
    1.55
    iz
    1.54
    নের
    1.54
    POSITIVE LOGITS
    ه
    2.59
     loafers
    2.48
    s
    2.38
    هما
    2.25
    eers
    2.17
     reprogramming
    2.08
    淆
    2.06
    てもら
    2.05
     jigs
    1.99
     climates
    1.97
    Act Density 0.026%

    No Known Activations