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

    Neuronpedia

    INDEX
    Explanations

    alphamind sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     namespaces
    0.64
     creators
    0.63
     JSX
    0.62
    NSInteger
    0.62
    dateFormat
    0.61
    なさ
    0.61
    ărul
    0.60
     popsicle
    0.60
     SYN
    0.60
     divs
    0.60
    POSITIVE LOGITS
    кого
    0.97
    orithm
    0.96
    chemist
    0.92
    batross
    0.90
    arming
    0.87
    cohols
    0.85
    trimenti
    0.84
     Qaeda
    0.84
     fresco
    0.84
    querque
    0.81
    Act Density 0.095%

    No Known Activations