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

    Neuronpedia

    INDEX
    Explanations

    header text after opening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وا
    0.91
    or
    0.87
    ast
    0.82
    مي
    0.82
    uot
    0.80
    izzle
    0.78
    og
    0.78
     measurement
    0.77
    ب
    0.76
    ัว
    0.74
    POSITIVE LOGITS
     Caledonia
    0.95
     Pradesh
    0.85
     thaliana
    0.85
     vimos
    0.84
     talaga
    0.83
     bodice
    0.82
    щего
    0.81
     coalgebras
    0.80
    ពិសេស
    0.80
     estatales
    0.80
    Act Density 0.000%

    No Known Activations