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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .RightToLeft
    -0.07
    aws
    -0.06
    .define
    -0.06
    až
    -0.06
     Zoo
    -0.06
     학생
    -0.06
     Weed
    -0.06
     eaten
    -0.06
     Qaeda
    -0.06
    TestingModule
    -0.06
    POSITIVE LOGITS
    ','#
    0.08
    #\
    0.07
    とする
    0.07
    豊
    0.07
    832
    0.07
     伊
    0.06
     Luk
    0.06
    _BIG
    0.06
    Titan
    0.06
    495
    0.06
    Act Density 0.000%

    No Known Activations