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

    Neuronpedia

    INDEX
    Explanations

    any request or task

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inutile
    0.46
     volut
    0.41
     facteurs
    0.41
     భాగ
    0.40
     इनो
    0.40
     enhancers
    0.39
     tiles
    0.39
    鍔
    0.39
     annular
    0.39
     애
    0.38
    POSITIVE LOGITS
     dowol
    1.08
     qualsiasi
    1.01
     cualquier
    0.96
    任何
    0.94
     qualunque
    0.93
     qualquer
    0.91
     कोणत्याही
    0.91
     любого
    0.90
     যেকোন
    0.89
     যেকোনো
    0.89
    Act Density 0.064%

    No Known Activations