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

    Neuronpedia

    INDEX
    Explanations

    category property assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.57
    י
    0.55
    的
    0.54
     are
    0.53
     Checked
    0.52
     Program
    0.51
    。
    0.48
     Backpack
    0.47
    बच्चों
    0.47
    の
    0.47
    POSITIVE LOGITS
    stellungen
    0.54
    onucle
    0.53
    stage
    0.52
    ordinal
    0.51
    iguation
    0.49
    numer
    0.49
     satire
    0.49
    malign
    0.49
    occur
    0.48
    ciaux
    0.48
    Act Density 0.000%

    No Known Activations