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

    Neuronpedia

    INDEX
    Explanations

    tokenization and word parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.95
    ……
    0.83
                                   
    0.76
    …
    0.75
     …
    0.68
            
    0.66
     (…)
    0.65
    <sup>
    0.64
    ...
    0.63
    …)
    0.63
    POSITIVE LOGITS
    ິກ
    0.82
    browserTarget
    0.82
    ❎
    0.80
     ,'
    0.80
    💹
    0.78
     <<"
    0.77
    벳
    0.76
     .”
    0.75
     ，
    0.75
    ሉ።
    0.74
    Act Density 0.005%

    No Known Activations