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

    Neuronpedia

    INDEX
    Explanations

    -bind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hottest
    -0.07
    lüğü
    -0.07
    *u
    -0.07
    attachments
    -0.07
     constitute
    -0.07
    大气
    -0.07
    -two
    -0.07
    妇
    -0.07
     indicative
    -0.06
    orientation
    -0.06
    POSITIVE LOGITS
     النظر
    0.07
     fandom
    0.07
    liced
    0.07
     fried
    0.07
    🇷
    0.07
     aborted
    0.07
     Installing
    0.07
    寶
    0.07
    鳎
    0.07
    皇上
    0.07
    Act Density 0.001%

    No Known Activations