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

    Neuronpedia

    INDEX
    Explanations

    structured output and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relais
    0.82
    asyonu
    0.77
     swamp
    0.76
     Abelian
    0.75
    ClrBit
    0.74
     abelian
    0.73
     мнение
    0.72
    ەیە
    0.72
     zeolite
    0.72
     Wap
    0.71
    POSITIVE LOGITS
    final
    0.81
    text
    0.78
     final
    0.78
    Final
    0.75
     Final
    0.75
    最終
    0.67
     text
    0.65
    Text
    0.62
     최종
    0.61
    最终
    0.61
    Act Density 0.001%

    No Known Activations