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

    Neuronpedia

    INDEX
    Explanations

    advice and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proud
    0.44
     στο
    0.44
     connue
    0.40
    ='
    0.40
     CFC
    0.38
    xC
    0.38
     orgull
    0.38
     nicely
    0.37
    ituus
    0.37
     bekannt
    0.37
    POSITIVE LOGITS
    اد
    0.45
     의견
    0.44
     обсу
    0.43
    lympi
    0.43
     출연
    0.41
    }^{+}+
    0.41
     feedbacks
    0.41
     asesin
    0.40
    攽
    0.40
     dissection
    0.39
    Act Density 0.000%

    No Known Activations