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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disgusted
    -0.07
    _FORM
    -0.06
     plu
    -0.06
     drown
    -0.06
     Regex
    -0.06
    扫
    -0.06
    ать
    -0.06
    .DialogResult
    -0.06
     searchData
    -0.06
    Formation
    -0.06
    POSITIVE LOGITS
     assertions
    0.08
    fred
    0.07
    ^{-
    0.06
     srdce
    0.06
    expense
    0.06
     KL
    0.06
     (((
    0.06
     gf
    0.06
     inset
    0.06
     ={↵
    0.06
    Act Density 0.041%

    No Known Activations