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

    Neuronpedia

    INDEX
    Explanations

    The letter s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.09
    ちょっと
    -0.07
    調整
    -0.07
    到现在
    -0.07
    atform
    -0.07
     legitimately
    -0.07
    ,num
    -0.07
    很多人都
    -0.07
     voluntarily
    -0.07
    —for
    -0.07
    POSITIVE LOGITS
     S
    0.12
    -s
    0.11
    S
    0.09
     s
    0.09
    -S
    0.08
    iosk
    0.08
    𝑊
    0.08
    ｓ
    0.08
    𐍃
    0.08
    	s
    0.08
    Act Density 0.150%

    No Known Activations