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

    Neuronpedia

    INDEX
    Explanations

    .

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scopes
    0.43
     recetas
    0.43
     sovi
    0.42
     هم
    0.42
    珑
    0.42
     spender
    0.42
     ممكن
    0.41
     lingue
    0.40
     markers
    0.40
     عن
    0.40
    POSITIVE LOGITS
    čina
    0.49
    یکه
    0.46
     Συν
    0.46
    ิ
    0.46
    換え
    0.45
    0.44
    亼
    0.44
    ０
    0.44
    کا
    0.43
    카
    0.43
    Act Density 0.003%

    No Known Activations