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

    Neuronpedia

    INDEX
    Explanations

    Both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.66
    entan
    -0.63
    GEBURTSDATUM
    -0.61
    eezy
    -0.57
     Chinese
    -0.57
    jsdelivr
    -0.56
     China
    -0.56
     legal
    -0.55
    Abitanti
    -0.54
    WidgetItem
    -0.54
    POSITIVE LOGITS
     mind
    0.71
    writeFieldEnd
    0.70
    mind
    0.55
     MIND
    0.53
     minds
    0.53
     خارجية
    0.53
     portefeuille
    0.49
    Mind
    0.49
    MIND
    0.47
     ffilmiau
    0.46
    Act Density 0.001%

    No Known Activations