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

    Neuronpedia

    INDEX
    Explanations

    análisis de experts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стым
    0.49
    тли
    0.42
    ancourt
    0.42
    ঘুম
    0.41
     everytime
    0.40
     oficina
    0.39
    শক
    0.38
    posX
    0.38
    XMLSchema
    0.38
     কর্মকর্ত
    0.37
    POSITIVE LOGITS
    ve
    0.48
     Plane
    0.45
     :
    0.42
     He
    0.42
     Newton
    0.42
     lob
    0.41
    Plane
    0.40
     Scope
    0.39
    ads
    0.39
    pi
    0.38
    Act Density 0.001%

    No Known Activations