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

    Neuronpedia

    INDEX
    Explanations

    medical conditions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     가지
    0.43
     reincarn
    0.42
    impression
    0.41
     Gaga
    0.41
    illustration
    0.41
     banal
    0.40
    偶尔
    0.40
    اری
    0.39
    込め
    0.39
    uale
    0.38
    POSITIVE LOGITS
    Datos
    0.50
     prioritizing
    0.49
     Pues
    0.47
     Amber
    0.47
     النش
    0.47
    Pues
    0.45
    ientras
    0.45
    Orden
    0.45
    uces
    0.44
    mensaje
    0.43
    Act Density 0.000%

    No Known Activations