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

    Neuronpedia

    INDEX
    Explanations

    compile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lost
    -0.07
    (hObject
    -0.07
    Offer
    -0.06
    อต
    -0.06
     gd
    -0.06
    obus
    -0.06
     ld
    -0.06
    _trees
    -0.06
    _sector
    -0.06
    Subject
    -0.06
    POSITIVE LOGITS
     tackle
    0.07
    πε
    0.06
     indispensable
    0.06
     guarantees
    0.06
    erva
    0.06
     φορ
    0.06
    @end
    0.06
     draft
    0.06
    淡
    0.06
    fight
    0.06
    Act Density 0.001%

    No Known Activations