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

    Neuronpedia

    INDEX
    Explanations

    Color gamut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harming
    -0.07
    кс
    -0.07
    connection
    -0.07
    .Cos
    -0.06
    uye
    -0.06
     페이지
    -0.06
    ход
    -0.06
    ldb
    -0.06
    number
    -0.06
    ovolta
    -0.06
    POSITIVE LOGITS
    	area
    0.06
    .groupControl
    0.06
     Default
    0.06
    ceiver
    0.06
     kli
    0.06
    住
    0.06
    .vehicle
    0.06
     renaming
    0.06
    _entry
    0.06
    /load
    0.06
    Act Density 0.011%

    No Known Activations