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

    Neuronpedia

    INDEX
    Explanations

    VFA, OGTT, neural networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েইলি
    0.72
     広
    0.70
     ভাত
    0.69
     изме
    0.67
    和社会
    0.67
     raccol
    0.65
     võimal
    0.63
    itatud
    0.63
     unavoidable
    0.63
     pharmacies
    0.62
    POSITIVE LOGITS
    де
    1.13
    Cartoon
    0.86
    сты
    0.84
    о
    0.80
    Test
    0.79
    be
    0.79
    вной
    0.78
    te
    0.77
    до
    0.77
    г
    0.76
    Act Density 0.001%

    No Known Activations