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

    Neuronpedia

    INDEX
    Explanations

    confirmation of appointments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    0.63
    北京市
    0.62
     interesado
    0.60
    osas
    0.59
    請
    0.59
    t
    0.59
    苚
    0.58
     fotografi
    0.57
     effettu
    0.57
     nasc
    0.56
    POSITIVE LOGITS
     “
    0.52
     Chunk
    0.51
     occurs
    0.49
     climbing
    0.49
     dental
    0.47
     organ
    0.47
    грам
    0.46
     his
    0.46
     knowing
    0.46
    ढ़ाई
    0.46
    Act Density 0.002%

    No Known Activations