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

    Neuronpedia

    INDEX
    Explanations

    security process, safety measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '));
    0.70
    ă
    0.70
    </i>
    0.67
    ());
    0.64
    üse
    0.64
    {
    0.64
    �
    0.64
    "));
    0.63
    im
    0.63
    est
    0.62
    POSITIVE LOGITS
     zahlreiche
    0.70
    ية
    0.66
     alemão
    0.64
     그는
    0.63
     jähr
    0.63
     रोजाना
    0.62
     cientos
    0.62
     spécialement
    0.62
    IDADE
    0.61
     angiogenic
    0.61
    Act Density 1.727%

    No Known Activations