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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ув
    -0.07
    ("{}
    -0.07
    stri
    -0.07
    edla
    -0.07
    APPLE
    -0.07
     almond
    -0.06
     reputation
    -0.06
    gold
    -0.06
     файл
    -0.06
     viewpoints
    -0.06
    POSITIVE LOGITS
     addicts
    0.07
    #get
    0.06
    findBy
    0.06
     hdf
    0.06
    ContentAlignment
    0.06
     Gör
    0.06
    EqualityComparer
    0.06
     Genç
    0.06
    ón
    0.06
    observe
    0.06
    Act Density 0.030%

    No Known Activations