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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *D
    -0.07
    ダ
    -0.07
    +d
    -0.07
     "==
    -0.07
    xA
    -0.07
     水
    -0.07
    	where
    -0.06
     ['',
    -0.06
    )&&
    -0.06
    	A
    -0.06
    POSITIVE LOGITS
    son
    0.09
    _{
    0.09
     tattoo
    0.08
    SON
    0.07
    _
    0.07
     Sisters
    0.07
    pton
    0.07
     on
    0.07
     Maiden
    0.07
    ton
    0.07
    Act Density 0.012%

    No Known Activations