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

    Neuronpedia

    INDEX
    Explanations

    purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hsv
    -0.07
     ژان
    -0.06
     bead
    -0.06
    飲
    -0.06
    	ON
    -0.06
    ۳۰
    -0.06
     ziy
    -0.06
     eight
    -0.06
     Ко
    -0.05
     win
    -0.05
    POSITIVE LOGITS
     Purpose
    0.11
     purpose
    0.10
     признач
    0.09
    -purpose
    0.08
    purpose
    0.08
     argues
    0.08
     αποτε
    0.08
    >Type
    0.07
     pulp
    0.07
    เพ
    0.07
    Act Density 0.018%

    No Known Activations