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

    Neuronpedia

    INDEX
    Explanations

    iterating a count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Century
    0.68
    ებლ
    0.67
     Eduardo
    0.65
     cư
    0.64
     određ
    0.64
    ებ
    0.62
    oser
    0.62
    ρεία
    0.62
    uncia
    0.61
    AbsolutePath
    0.61
    POSITIVE LOGITS
     সংখ্যক
    1.22
    个
    1.02
    সংখ্যক
    0.95
     integers
    0.93
    usize
    0.91
     elements
    0.89
     qubits
    0.89
     rows
    0.89
    個
    0.88
    개의
    0.87
    Act Density 0.607%

    No Known Activations