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

    Neuronpedia

    INDEX
    Explanations

    computer systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    具有
    -0.08
    нский
    -0.08
    ינה
    -0.07
     éxito
    -0.07
    xito
    -0.07
    들에게
    -0.07
    irmingham
    -0.07
     Damon
    -0.06
     Florida
    -0.06
     pops
    -0.06
    POSITIVE LOGITS
    碎
    0.07
    玖
    0.07
    	ext
    0.07
    /board
    0.07
    Mich
    0.07
    fk
    0.07
    (norm
    0.06
    =pd
    0.06
    (board
    0.06
    黑色
    0.06
    Act Density 0.331%

    No Known Activations