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

    Neuronpedia

    INDEX
    Explanations

    cnt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rigs
    -0.07
     yourself
    -0.07
     fame
    -0.07
     pushing
    -0.07
     Computer
    -0.07
     expected
    -0.07
     emotion
    -0.06
     starters
    -0.06
     spreading
    -0.06
     shoved
    -0.06
    POSITIVE LOGITS
     Addition
    0.06
    	dev
    0.06
    ذ
    0.06
    OPTION
    0.06
     cư
    0.06
     brilliantly
    0.06
    /library
    0.06
    /sweetalert
    0.06
     bran
    0.06
    _tac
    0.06
    Act Density 0.091%

    No Known Activations