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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ferry
    -0.06
     mě
    -0.06
     meisjes
    -0.06
     MON
    -0.06
     symb
    -0.06
     consum
    -0.06
     Mum
    -0.06
     debe
    -0.06
     Wet
    -0.06
     incapable
    -0.06
    POSITIVE LOGITS
    خاب
    0.07
    aktu
    0.07
    』
    0.07
    scription
    0.07
    clientId
    0.07
    widget
    0.07
    llum
    0.06
    委
    0.06
    ponsible
    0.06
    lico
    0.06
    Act Density 0.027%

    No Known Activations