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

    Neuronpedia

    INDEX
    Explanations

    GAG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.71
     חיצוניים
    -0.70
    uxxxx
    -0.69
    iastes
    -0.65
    findpost
    -0.62
     насељу
    -0.60
     biografias
    -0.59
    Erreferentziak
    -0.59
    MessageOf
    -0.59
     незавершена
    -0.58
    POSITIVE LOGITS
    ressive
    0.57
    ‍♀️
    0.52
    ivo
    0.52
     alimentaire
    0.51
    ressional
    0.49
    ‍♂️
    0.48
    ht
    0.48
    ര
    0.47
    cyon
    0.47
    hep
    0.47
    Act Density 0.013%

    No Known Activations