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

    Neuronpedia

    INDEX
    Explanations

    performing actions or operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supergiants
    0.82
     genes
    0.80
     composants
    0.80
     perished
    0.78
     lymphocytes
    0.77
     intellectuals
    0.74
     terbaru
    0.72
     inimes
    0.71
     monsters
    0.71
     masterpieces
    0.71
    POSITIVE LOGITS
    这项
    0.80
    Asimismo
    0.75
     عمليه
    0.75
    Фу
    0.73
    Ла
    0.71
    Diese
    0.70
    同様
    0.70
    と同様
    0.70
    Algun
    0.68
     చిన్న
    0.68
    Act Density 1.041%

    No Known Activations