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

    Neuronpedia

    INDEX
    Explanations

    research paper discussions/summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     תח
    -0.08
     instaur
    -0.08
     défin
    -0.08
    owa
    -0.08
     gushy
    -0.08
    شطة
    -0.07
    šk
    -0.07
     duha
    -0.07
     الدعم
    -0.07
    To
    -0.07
    POSITIVE LOGITS
     Unexpected
    0.09
     contrasted
    0.09
     Ü
    0.09
     совп
    0.09
     findings
    0.09
     inesper
    0.08
     unexpected
    0.08
     overeen
    0.08
     discrep
    0.08
     matches
    0.08
    Act Density 0.007%

    No Known Activations