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

    Neuronpedia

    INDEX
    Explanations

    listing numbers or letters before words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Grady
    0.30
    াধি
    0.30
    ({},
    0.29
    Literal
    0.29
    >{</
    0.28
    ρίς
    0.28
    inée
    0.27
     জেলে
    0.27
    卷积
    0.27
    的变化
    0.27
    POSITIVE LOGITS
     masch
    0.31
     스
    0.31
    ಅ
    0.31
     नौ
    0.30
    नवीन
    0.30
     dezvolt
    0.29
     शेवट
    0.29
    のス
    0.29
     impresionante
    0.29
     prolific
    0.28
    Act Density 0.060%

    No Known Activations