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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	child
    -0.07
    iral
    -0.07
     Entity
    -0.07
     Tv
    -0.06
    	layout
    -0.06
     Typ
    -0.06
     arms
    -0.06
    \x
    -0.06
     accounting
    -0.06
     escapes
    -0.06
    POSITIVE LOGITS
    	RTCT
    0.07
    嗎
    0.06
     {[%
    0.06
    (?:
    0.06
    /]
    0.06
     　
    0.06
    /*/
    0.06
    출장안마
    0.06
    constraints
    0.06
    _SIGN
    0.06
    Act Density 0.014%

    No Known Activations