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

    Neuronpedia

    INDEX
    Explanations

    async functions, neural networks, spreadsheets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Am
    0.50
     contexte
    0.50
    N
    0.49
    James
    0.47
    とても
    0.47
    ﾅ
    0.46
    Philadelphia
    0.46
    Georgia
    0.45
    Lieutenant
    0.45
    세계
    0.44
    POSITIVE LOGITS
     могут
    0.49
     straws
    0.47
     indican
    0.47
    ر
    0.47
    ikesh
    0.46
     môžu
    0.46
    znak
    0.46
     Escola
    0.45
     outcrops
    0.45
     sensors
    0.45
    Act Density 0.003%

    No Known Activations