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

    Neuronpedia

    INDEX
    Explanations

    descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     მთავ
    0.48
    重要な
    0.45
     psychotic
    0.45
     مهم
    0.44
     horrible
    0.43
     ergodic
    0.43
    pyrimidin
    0.43
     pathetic
    0.42
     heinous
    0.42
     catalysts
    0.42
    POSITIVE LOGITS
     разно
    0.44
     tended
    0.42
     moulded
    0.42
     vorhand
    0.41
     Incl
    0.41
    stick
    0.40
     slim
    0.39
    加强
    0.39
     protected
    0.38
     Supp
    0.38
    Act Density 0.001%

    No Known Activations