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

    Neuronpedia

    INDEX
    Explanations

    cloud and platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ắp
    0.32
    erna
    0.30
    escens
    0.29
    lgan
    0.29
    ningar
    0.29
    ningarna
    0.27
     disposiciones
    0.27
     нулю
    0.27
    sü
    0.26
    section
    0.26
    POSITIVE LOGITS
     platforms
    0.88
     platform
    0.76
    平台
    0.73
     платформа
    0.70
    平台的
    0.70
     plataformas
    0.69
    platforms
    0.68
     платфор
    0.65
     플랫폼
    0.65
     plataforma
    0.62
    Act Density 0.345%

    No Known Activations