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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	title
    -0.06
     ET
    -0.06
     Achilles
    -0.06
    mel
    -0.06
     matriz
    -0.06
    ansı
    -0.06
    Name
    -0.06
    rish
    -0.06
     Prep
    -0.06
    thanks
    -0.06
    POSITIVE LOGITS
     fury
    0.07
    _sex
    0.07
    _recv
    0.07
     ogs
    0.06
    €↵
    0.06
     прибы
    0.06
    (posts
    0.06
    -news
    0.06
     clears
    0.06
    .waitFor
    0.06
    Act Density 0.005%

    No Known Activations