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

    Neuronpedia

    INDEX
    Explanations

    add_attribute, generate_odd_numbers, extract_numbers, remove_dir

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.86
     опять
    0.73
    ,
    0.72
    !
    0.72
    ;
    0.70
     huge
    0.68
     ingenious
    0.67
     ourselves
    0.66
    also
    0.66
     also
    0.66
    POSITIVE LOGITS
     {@
    0.97
    {@
    0.84
    ṕ
    0.81
    ྵ
    0.79
    ہرے
    0.77
    ത്തിക
    0.75
    ňuje
    0.75
    ᓚ
    0.74
     می‌کند
    0.73
     contém
    0.73
    Act Density 0.728%

    No Known Activations