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

    Neuronpedia

    INDEX
    Explanations

    describe or implement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consistente
    0.47
    Ꮰ
    0.45
     regreso
    0.44
    ក៏
    0.43
    ပါသည်။
    0.43
    nov
    0.43
    vr
    0.42
    ㄚ
    0.42
    zoeken
    0.42
    हून
    0.42
    POSITIVE LOGITS
    典型
    0.46
     রচিত
    0.45
    伝統
    0.43
    实行
    0.41
     전통
    0.41
     décrit
    0.41
     center
    0.40
    発達
    0.40
     relais
    0.40
     semifinals
    0.39
    Act Density 0.005%

    No Known Activations