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

    Neuronpedia

    INDEX
    Explanations

    Okay, conversational starter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ap
    0.55
    ie
    0.46
    pleri
    0.46
    ot
    0.45
    it
    0.44
    astom
    0.44
    trace
    0.43
    atoren
    0.43
    ast
    0.42
    ab
    0.42
    POSITIVE LOGITS
    ﺬ
    0.48
     induces
    0.47
     rosso
    0.47
     motivates
    0.46
    セ
    0.46
     aunts
    0.45
    れて
    0.45
    低下
    0.45
     catalyzes
    0.45
     passare
    0.44
    Act Density 0.002%

    No Known Activations