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

    Neuronpedia

    INDEX
    Explanations

    harmful or abusive acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     centroids
    0.49
    мин
    0.49
    FOREIGN
    0.48
     COMPLEXES
    0.47
    리를
    0.45
    sphere
    0.44
    claves
    0.44
     complexes
    0.44
     ಅವನು
    0.44
    ৩৭
    0.43
    POSITIVE LOGITS
    ည်း
    0.57
     an
    0.46
     fic
    0.45
     accomplished
    0.44
     সঙ্গ
    0.44
     franz
    0.43
    …?
    0.42
     first
    0.42
     quizz
    0.42
     કોઈ
    0.42
    Act Density 0.015%

    No Known Activations