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
    458
    -0.07
    020
    -0.07
    170
    -0.07
     ekip
    -0.06
     Hearts
    -0.06
    213
    -0.06
     відк
    -0.06
     ign
    -0.06
    922
    -0.06
     гол
    -0.06
    POSITIVE LOGITS
    elligence
    0.08
    _method
    0.07
     dismal
    0.07
     apparently
    0.07
    $d
    0.07
    _expression
    0.06
     sims
    0.06
     readme
    0.06
     datingside
    0.06
     syntax
    0.06
    Act Density 0.015%

    No Known Activations