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

    Neuronpedia

    INDEX
    Explanations

    highly charged disparaging political rhetoric

    oai_token-act-pair · gemini-2.0-flash

    political insults

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estekak
    -0.72
    errHandler
    -0.68
    xtext
    -0.59
    entyfik
    -0.58
     généraux
    -0.57
    rungsseite
    -0.57
    WritableDatabase
    -0.56
    tijds
    -0.56
     élevées
    -0.56
     Schuh
    -0.54
    POSITIVE LOGITS
     meek
    0.65
     helpless
    0.56
     propOrder
    0.55
     pitt
    0.51
     nerf
    0.51
     submissive
    0.49
    TextAppearance
    0.49
    oprecip
    0.48
     wim
    0.48
     cowards
    0.48
    Act Density 0.886%

    No Known Activations