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

    Neuronpedia

    INDEX
    Explanations

    cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hogy
    -0.06
    _IMP
    -0.06
    ."
    -0.06
    (pixel
    -0.06
     bagi
    -0.06
     billionaires
    -0.06
    Mp
    -0.06
     постоянно
    -0.06
    olics
    -0.06
     pochop
    -0.06
    POSITIVE LOGITS
     Ont
    0.07
    .PrimaryKey
    0.07
     she
    0.07
    @Service
    0.07
     replace
    0.06
    -shadow
    0.06
     finishing
    0.06
     그가
    0.06
     connectivity
    0.06
    .volley
    0.06
    Act Density 0.008%

    No Known Activations