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

    Neuronpedia

    INDEX
    Explanations

    Search

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IBM
    -0.07
     uçak
    -0.06
    587
    -0.06
     bet
    -0.06
    _props
    -0.06
     Rubin
    -0.05
    -on
    -0.05
    ео
    -0.05
     inactive
    -0.05
    -holder
    -0.05
    POSITIVE LOGITS
    丰
    0.06
    OMUX
    0.06
    .filter
    0.06
     hammer
    0.06
     Conservative
    0.06
    CTION
    0.06
     Petersburg
    0.06
    .export
    0.06
    Names
    0.06
    .EMPTY
    0.06
    Act Density 0.031%

    No Known Activations