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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reducer
    -0.07
     //.
    -0.07
    (interface
    -0.06
     XCT
    -0.06
     lut
    -0.06
    .gson
    -0.06
    少し
    -0.06
    _MATH
    -0.06
    voř
    -0.06
     doGet
    -0.06
    POSITIVE LOGITS
    ptions
    0.07
    \-
    0.07
     islands
    0.07
     поверх
    0.07
     casino
    0.07
     arrived
    0.06
    roph
    0.06
     permitted
    0.06
    ANDING
    0.06
     Arguments
    0.06
    Act Density 0.076%

    No Known Activations