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

    Neuronpedia

    INDEX
    Explanations

    Neurological outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ő
    -0.07
     builtin
    -0.07
    -worthy
    -0.06
    nah
    -0.06
    νος
    -0.06
    bbbb
    -0.06
     Jose
    -0.06
    andles
    -0.06
     multer
    -0.06
    敵
    -0.06
    POSITIVE LOGITS
    意识
    0.07
    	TokenName
    0.06
     Bliss
    0.06
    semicolon
    0.06
    xEE
    0.06
    ifik
    0.06
     گیاه
    0.06
     dollar
    0.06
     Nuggets
    0.06
    Boom
    0.06
    Act Density 0.039%

    No Known Activations