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

    Neuronpedia

    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ebola
    -0.07
     Demp
    -0.07
    craper
    -0.07
     htons
    -0.06
     Newport
    -0.06
    Vect
    -0.06
     early
    -0.06
    #↵
    -0.06
    	UP
    -0.06
    ub
    -0.06
    POSITIVE LOGITS
    령
    0.07
    .sql
    0.06
     명
    0.06
    .json
    0.06
     پي
    0.06
     Baron
    0.06
    manent
    0.06
     çöz
    0.06
    0.06
    0.06
    Act Density 0.000%

    No Known Activations