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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sons
    -0.07
     הספר
    -0.07
    _cycles
    -0.06
     ANAL
    -0.06
    marsh
    -0.06
    🚕
    -0.06
    SCREEN
    -0.06
     Neutral
    -0.06
    _DIP
    -0.06
    Heart
    -0.06
    POSITIVE LOGITS
    bol
    0.08
    uba
    0.08
    衽
    0.06
    ım
    0.06
     gắng
    0.06
    עמ
    0.06
     frei
    0.06
    整整
    0.06
    	body
    0.06
    为目的
    0.06
    Act Density 0.044%

    No Known Activations