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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bulky
    -0.08
    县城
    -0.07
    籴
    -0.07
    _database
    -0.07
     servic
    -0.07
     ساب
    -0.07
    _prime
    -0.07
     gmail
    -0.07
    /mL
    -0.07
    /name
    -0.07
    POSITIVE LOGITS
    …the
    0.07
    (app
    0.07
    Notifications
    0.06
     Abyss
    0.06
    iet
    0.06
    陰
    0.06
    ꕥ
    0.06
    。（
    0.06
    てしまいます
    0.06
    (function
    0.06
    Act Density 0.026%

    No Known Activations