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

    Neuronpedia

    INDEX
    Explanations

    retro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [E
    -0.07
    Fin
    -0.07
    zell
    -0.07
     jente
    -0.06
     plants
    -0.06
     ARM
    -0.06
     withString
    -0.06
     Crush
    -0.06
     comrades
    -0.06
    raf
    -0.06
    POSITIVE LOGITS
     faithfully
    0.07
     numeric
    0.07
    upaten
    0.07
     temiz
    0.06
     gastro
    0.06
    ToWorld
    0.06
     procrast
    0.06
    บาย
    0.06
    requestCode
    0.06
    pectrum
    0.06
    Act Density 0.001%

    No Known Activations