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

    Neuronpedia

    INDEX
    Explanations

    ** or : followed by code/markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ((
    0.75
    ([],
    0.70
    ({},
    0.70
    "(
    0.67
    [-]
    0.66
    [-
    0.65
    "...
    0.64
    ("/")
    0.62
    (("
    0.61
    ((-
    0.61
    POSITIVE LOGITS
    <strong>
    0.70
     también
    0.69
     גם
    0.67
     também
    0.67
     nCenters
    0.67
     OÜ
    0.67
    ucose
    0.66
     auxqu
    0.66
     грн
    0.65
     શુભ
    0.65
    Act Density 0.578%

    No Known Activations