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

    Neuronpedia

    INDEX
    Explanations

    healthline topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Psychological
    0.53
     психо
    0.52
    🩺
    0.52
    ඖ
    0.52
     மருத்துவ
    0.51
    心理
    0.49
    Psych
    0.48
     आयुर्वे
    0.48
     psychological
    0.47
     психологи
    0.46
    POSITIVE LOGITS
    读取
    0.42
     pid
    0.40
    ->
    0.37
    ثير
    0.37
     nonzero
    0.36
     चालू
    0.36
    Keeper
    0.36
    墟
    0.36
     sido
    0.36
    デ
    0.36
    Act Density 0.003%

    No Known Activations