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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uming
    0.45
    uling
    0.45
     Vector
    0.44
     Correlations
    0.44
    的项目
    0.43
    uteurs
    0.42
    ultz
    0.42
    $),
    0.42
    ubi
    0.42
     Plots
    0.42
    POSITIVE LOGITS
    ת
    0.49
    м
    0.48
     подрост
    0.48
     חש
    0.46
    Oxygen
    0.43
    t
    0.43
    ям
    0.43
    времен
    0.43
    م
    0.42
     distill
    0.42
    Act Density 0.002%

    No Known Activations