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

    Neuronpedia

    INDEX
    Explanations

    system changes event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     due
    -0.81
     ≤
    -0.81
     зап
    -0.81
     Negra
    -0.79
    Critical
    -0.78
     vital
    -0.77
     alba
    -0.75
    ционные
    -0.75
     numa
    -0.74
    🥄
    -0.73
    POSITIVE LOGITS
    ่ะ
    0.85
    美好的
    0.81
    Sera
    0.79
    Asu
    0.78
     веществ
    0.77
    miş
    0.75
     copertura
    0.73
    Monter
    0.72
     estacionamento
    0.70
    IsNotEmpty
    0.69
    Act Density 0.007%

    No Known Activations