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

    Neuronpedia

    INDEX
    Explanations

    (new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruler
    -0.07
    Contains
    -0.07
    ('_
    -0.07
     Violence
    -0.07
    γη
    -0.07
     relatively
    -0.07
    소개
    -0.07
    _floor
    -0.06
    in
    -0.06
     Travis
    -0.06
    POSITIVE LOGITS
    だな
    0.06
     libre
    0.06
    .Var
    0.06
     lắng
    0.06
     bigotry
    0.06
     TEAM
    0.06
     TELE
    0.06
    ORIGINAL
    0.06
     muschi
    0.06
    (headers
    0.06
    Act Density 0.018%

    No Known Activations