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

    Neuronpedia

    INDEX
    Explanations

    ฤ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elegant
    -0.07
     тен
    -0.07
    Ơ
    -0.07
    лова
    -0.07
    -banner
    -0.06
    AMERA
    -0.06
    птом
    -0.06
    .payment
    -0.06
    ,String
    -0.06
     Rental
    -0.06
    POSITIVE LOGITS
     minimal
    0.06
    Increased
    0.06
    .best
    0.06
     obr
    0.06
     evacuated
    0.06
    inline
    0.06
     Inf
    0.06
    _cost
    0.06
    cmp
    0.06
     exercising
    0.06
    Act Density 0.009%

    No Known Activations