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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scalar
    -0.07
     xấu
    -0.07
     alone
    -0.06
     vanilla
    -0.06
    _HE
    -0.06
     KG
    -0.06
    frared
    -0.06
    Theta
    -0.06
     вим
    -0.06
    ुछ
    -0.06
    POSITIVE LOGITS
    史
    0.08
    \data
    0.06
     uri
    0.06
    	
↵
↵
    0.06
     conqu
    0.06
     McC
    0.06
    oppable
    0.06
     praw
    0.06
    quit
    0.06
     bew
    0.05
    Act Density 0.044%

    No Known Activations