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

    Neuronpedia

    INDEX
    Explanations

    say "s" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    汋
    0.39
    者に
    0.38
    бай
    0.38
    匼
    0.35
    انہ
    0.35
    <unused70>
    0.34
    rí
    0.34
     altına
    0.34
    튬
    0.34
     FN
    0.33
    POSITIVE LOGITS
    integral
    0.43
    Oi
    0.41
     kw
    0.41
    ഭവ
    0.39
    fuel
    0.38
     nw
    0.38
     Brem
    0.36
    Da
    0.36
    xbox
    0.36
    ISTANCE
    0.35
    Act Density 0.001%

    No Known Activations