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

    Neuronpedia

    INDEX
    Explanations

    branch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Primer
    -0.06
    ../../../
    -0.06
    Lo
    -0.06
     JsonObject
    -0.06
     booklet
    -0.06
     toolkit
    -0.06
    .IC
    -0.06
    Anne
    -0.06
    myp
    -0.06
    빛
    -0.06
    POSITIVE LOGITS
     Pyongyang
    0.07
    改革
    0.07
    NZ
    0.06
     drafting
    0.06
    ROAD
    0.06
    assa
    0.06
     spokesperson
    0.06
     boyunca
    0.06
    CAA
    0.06
     باغ
    0.06
    Act Density 0.002%

    No Known Activations