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

    Neuronpedia

    INDEX
    Explanations

    diseases, organs, and symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    der
    0.71
    ing
    0.71
    ാൽ
    0.67
     proponent
    0.67
     more
    0.65
    er
    0.64
     principales
    0.64
    ne
    0.64
    tu
    0.64
    r
    0.63
    POSITIVE LOGITS
     disorders
    1.00
     abnormalities
    0.98
     órg
    0.95
    𝙣
    0.95
     Erkrank
    0.94
     Symptoms
    0.93
     worsened
    0.92
     hyperplasia
    0.92
     erection
    0.90
     symptoms
    0.90
    Act Density 0.226%

    No Known Activations