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

    Neuronpedia

    INDEX
    Explanations

    describing specific situations or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     version
    0.96
     versions
    0.95
     iteration
    0.93
    version
    0.88
     implementation
    0.88
    版本
    0.85
     Versions
    0.84
     versión
    0.83
     incarnation
    0.81
     versiones
    0.81
    POSITIVE LOGITS
     phenomena
    1.20
     событий
    1.12
     phénomène
    1.11
     situations
    1.10
     wydar
    1.10
     events
    1.08
     diseases
    1.08
     Ereign
    1.08
     illnesses
    1.07
    事物
    1.07
    Act Density 0.943%

    No Known Activations