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

    Neuronpedia

    INDEX
    Explanations

    person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EFR
    -0.08
    .debugLine
    -0.07
     word
    -0.07
    Flow
    -0.07
    冏
    -0.07
     ############################################################################
    -0.06
                      ↵
    -0.06
     suk
    -0.06
     niezb
    -0.06
    (hObject
    -0.06
    POSITIVE LOGITS
     Pist
    0.08
    conde
    0.07
     Gupta
    0.07
     Myst
    0.07
    ками
    0.07
    섵
    0.07
     получения
    0.07
    possible
    0.07
    Polit
    0.07
    riages
    0.07
    Act Density 0.066%

    No Known Activations