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

    Neuronpedia

    INDEX
    Explanations

    spelling rules and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rhe
    0.46
     recor
    0.45
    鱻
    0.45
    CreationFailed
    0.45
    ēs
    0.44
    яз
    0.43
    يًا
    0.43
     tenacious
    0.43
     forze
    0.43
    वेशन
    0.42
    POSITIVE LOGITS
    <0x80>
    0.45
     μόνο
    0.43
     bungalows
    0.42
     掛け
    0.41
     ONLY
    0.40
    ας
    0.39
     saddhim
    0.39
    γμα
    0.39
     contracts
    0.38
     Angola
    0.38
    Act Density 0.007%

    No Known Activations