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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ATH
    -0.09
    ђе
    -0.09
     בדיוק
    -0.09
    Bueno
    -0.08
    Wikipedia
    -0.08
     생활
    -0.08
    culoskeletal
    -0.08
    đe
    -0.08
     Ebay
    -0.08
    cribes
    -0.08
    POSITIVE LOGITS
     frontier
    0.07
     Setting
    0.07
     normally
    0.07
    ">
↵
    0.07
     incompat
    0.07
     highlighting
    0.07
     resource
    0.07
     increasing
    0.06
     In
    0.06
     refinement
    0.06
    Act Density 0.004%

    No Known Activations