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

    Neuronpedia

    INDEX
    Explanations

    combinations and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सीक्व
    0.50
    relser
    0.49
     पाली
    0.48
    ുന്നു
    0.47
    ofthe
    0.47
    ങ്ങള്‍
    0.45
    系の
    0.44
     seascape
    0.44
     linguistique
    0.44
    ία
    0.44
    POSITIVE LOGITS
    vi
    0.49
     примене
    0.48
    hibit
    0.47
     профессор
    0.44
     измене
    0.44
    &#
    0.43
     فرص
    0.43
     жиз
    0.43
    ຮູ້
    0.43
    有机会
    0.43
    Act Density 0.000%

    No Known Activations