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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    332
    -0.08
    508
    -0.07
     dinosaurs
    -0.07
    496
    -0.07
    istorical
    -0.06
    ipzig
    -0.06
     TPP
    -0.06
    nest
    -0.06
     인구
    -0.06
    osaurs
    -0.06
    POSITIVE LOGITS
     уда
    0.07
    ()↵↵↵↵
    0.06
    responseData
    0.06
    redict
    0.06
     Portug
    0.06
    Grace
    0.06
    opies
    0.06
     disqualified
    0.06
     modelling
    0.06
    sealed
    0.06
    Act Density 0.011%

    No Known Activations