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

    Neuronpedia

    INDEX
    Explanations

    Cartographer of Lost Things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iré
    0.61
    iker
    0.48
    рав
    0.46
    υκ
    0.43
    уз
    0.43
    middleware
    0.42
    Quartz
    0.42
    utilisateur
    0.41
    Analyzing
    0.41
    setAdapter
    0.41
    POSITIVE LOGITS
     Copern
    0.47
     ९
    0.46
     ۶
    0.46
     Schild
    0.46
     andRow
    0.45
     eigenvector
    0.44
     धर
    0.43
     ۸
    0.43
    示范
    0.43
     eta
    0.43
    Act Density 0.005%

    No Known Activations