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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    precedented
    -0.07
    ，加
    -0.07
     jer
    -0.06
    diet
    -0.06
    CUR
    -0.06
    fir
    -0.06
    δε
    -0.06
     infographic
    -0.06
     Fav
    -0.06
    �택
    -0.06
    POSITIVE LOGITS
     potato
    0.08
     Battle
    0.07
     skilled
    0.07
     روسی
    0.06
    nem
    0.06
     Exact
    0.06
    Battle
    0.06
    alet
    0.06
    %"↵
    0.06
    	connection
    0.06
    Act Density 0.000%

    No Known Activations