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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    最新
    -0.06
    投資
    -0.06
    .water
    -0.06
     robbery
    -0.06
     متعدد
    -0.06
    LAS
    -0.06
    .Val
    -0.06
    	dp
    -0.06
    Authenticated
    -0.05
    음을
    -0.05
    POSITIVE LOGITS
     měsíce
    0.07
    鄉
    0.07
     dads
    0.07
     democratic
    0.06
    zerbai
    0.06
    psych
    0.06
     dead
    0.06
    having
    0.06
    створ
    0.06
     공고
    0.06
    Act Density 0.001%

    No Known Activations