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

    Neuronpedia

    INDEX
    Explanations

    Random letter sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ANY
    -0.07
    258
    -0.07
    sol
    -0.07
     vous
    -0.06
    536
    -0.06
    758
    -0.06
     esposa
    -0.06
     Avust
    -0.06
     oste
    -0.06
     sce
    -0.06
    POSITIVE LOGITS
     pp
    0.11
     BB
    0.10
    GG
    0.09
     MM
    0.09
    BB
    0.09
    pp
    0.09
     PP
    0.09
    ww
    0.09
     TT
    0.08
     HH
    0.08
    Act Density 0.078%

    No Known Activations