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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нике
    -0.07
     lidí
    -0.06
    亡
    -0.06
    солют
    -0.06
     изб
    -0.06
    -move
    -0.06
    getExtension
    -0.06
    anship
    -0.06
    orld
    -0.06
     حف
    -0.06
    POSITIVE LOGITS
    platz
    0.07
    ać
    0.07
     |--
    0.06
     --↵
    0.06
    :no
    0.06
    .Ag
    0.06
    ,)↵
    0.06
    ","");↵
    0.06
     vlast
    0.06
    	N
    0.06
    Act Density 0.025%

    No Known Activations