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

    Neuronpedia

    INDEX
    Explanations

    holds Items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OCA
    0.46
    -->
    0.46
     Makan
    0.46
    akanan
    0.45
     Insel
    0.44
     Mocha
    0.44
    遐
    0.44
    <unused573>
    0.44
     Moist
    0.44
     :");
    0.43
    POSITIVE LOGITS
    ام
    0.53
    ﺔ
    0.52
    年齢
    0.50
    ні
    0.49
    ेशन
    0.49
    experience
    0.49
     inflicted
    0.49
     experienced
    0.49
    теру
    0.47
     plummet
    0.47
    Act Density 0.000%

    No Known Activations