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

    Neuronpedia

    INDEX
    Explanations

    separating list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.99
    "/"
    0.95
    ,/
    0.94
     Others
    0.86
    ()/
    0.79
    -/
    0.79
    อื่น
    0.78
    ;/
    0.77
     /
    0.77
    Autres
    0.77
    POSITIVE LOGITS
     respectively
    0.70
     ¡
    0.55
    respectively
    0.54
     ஆகிய
    0.54
     injury
    0.48
    oxyl
    0.47
     empathy
    0.47
    appell
    0.46
     majd
    0.45
     ­
    0.44
    Act Density 0.693%

    No Known Activations