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

    Neuronpedia

    INDEX
    Explanations

    "Text HOME"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     edgecolor
    0.39
    Bau
    0.36
    背面
    0.36
     मौलिक
    0.35
     Pau
    0.35
    Ella
    0.35
    Elemental
    0.35
     हाता
    0.34
    adora
    0.34
     Bant
    0.34
    POSITIVE LOGITS
     dijel
    0.40
    нд
    0.36
    زم
    0.34
     tamb
    0.34
    UND
    0.33
    quirements
    0.33
     disso
    0.33
     hey
    0.33
    लिया
    0.33
     jir
    0.33
    Act Density 0.009%

    No Known Activations