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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ानस
    -0.07
    kara
    -0.06
    
    -0.06
    -0.06
    ㅋ
    -0.06
    hawks
    -0.06
     Motors
    -0.06
    kud
    -0.06
    -lang
    -0.06
    ungeon
    -0.06
    POSITIVE LOGITS
     Celebration
    0.07
     весь
    0.06
     engage
    0.06
     HttpMethod
    0.06
     Image
    0.06
     Rutgers
    0.06
     deutsche
    0.06
     Sunshine
    0.06
    153
    0.06
     Exodus
    0.06
    Act Density 0.014%

    No Known Activations