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

    Neuronpedia

    INDEX
    Explanations

    shopping deals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conversion
    -0.07
     indicates
    -0.07
     hostages
    -0.07
    ры
    -0.07
     flair
    -0.06
     brackets
    -0.06
     meltdown
    -0.06
    (interval
    -0.06
     chambers
    -0.06
    lok
    -0.06
    POSITIVE LOGITS
    �다
    0.06
     scant
    0.06
    .MouseEventHandler
    0.06
     зависит
    0.06
     Rupert
    0.06
    peng
    0.06
     концентра
    0.06
    secret
    0.06
     annum
    0.05
     krev
    0.05
    Act Density 0.047%

    No Known Activations