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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (HTTP
    -0.07
     już
    -0.06
    ruptions
    -0.06
    (IT
    -0.06
     ancor
    -0.06
    otonin
    -0.06
    -guard
    -0.06
    	It
    -0.06
    oke
    -0.06
    -----
    -0.06
    POSITIVE LOGITS
     Marion
    0.07
     пров
    0.07
     responders
    0.06
     Jes
    0.06
    .res
    0.06
     Rabbi
    0.06
    igDecimal
    0.06
    signature
    0.06
    /respond
    0.06
    	screen
    0.06
    Act Density 0.003%

    No Known Activations