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

    Neuronpedia

    INDEX
    Explanations

    fit into, divide into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जिस
    0.41
     மட்டுமல்ல
    0.41
     revolutionized
    0.40
    ziem
    0.40
    学的
    0.39
    contrad
    0.38
     ∞
    0.38
     sinned
    0.38
    becomes
    0.37
     మరి
    0.37
    POSITIVE LOGITS
     supernatants
    0.41
    itäten
    0.40
    Past
    0.39
    angga
    0.39
    ہائی
    0.38
     वोटों
    0.38
    才能
    0.38
    Factors
    0.37
    UNT
    0.36
    Usuarios
    0.36
    Act Density 0.001%

    No Known Activations