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

    Neuronpedia

    INDEX
    Explanations

    open parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tồ
    -0.08
    ampire
    -0.08
     בדי
    -0.08
    诚实
    -0.07
     Tolkien
    -0.07
     migr
    -0.07
    Localized
    -0.07
     подпис
    -0.07
     choosing
    -0.07
    _physical
    -0.06
    POSITIVE LOGITS
     preserved
    0.07
    要点
    0.07
     cliff
    0.07
    ▄
    0.07
    #####
    0.07
    處
    0.07
     News
    0.07
    -css
    0.06
    utra
    0.06
    -x
    0.06
    Act Density 0.002%

    No Known Activations