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

    Neuronpedia

    INDEX
    Explanations

    smooth, slippery, characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olds
    0.40
     Physicians
    0.39
     عالية
    0.39
    old
    0.38
    rund
    0.38
     سع
    0.38
    ંતુ
    0.37
    igers
    0.37
     R
    0.36
     Physician
    0.36
    POSITIVE LOGITS
     characteristics
    0.41
     karakteristik
    0.40
     लक्षण
    0.40
    Characteristics
    0.40
     alá
    0.40
     Características
    0.39
    数目
    0.39
     глубо
    0.39
    Floating
    0.38
     mystic
    0.38
    Act Density 0.002%

    No Known Activations