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

    Neuronpedia

    INDEX
    Explanations

    Code hashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surve
    -0.07
    _Parms
    -0.07
    turned
    -0.06
     sponge
    -0.06
     Bend
    -0.06
    sound
    -0.06
     miraculous
    -0.06
    _indicator
    -0.06
    補
    -0.06
    _text
    -0.06
    POSITIVE LOGITS
     simplicity
    0.07
    osy
    0.06
     μπορεί
    0.06
    689
    0.06
     계속
    0.06
    393
    0.06
    aira
    0.06
     лекар
    0.06
     titre
    0.06
    772
    0.06
    Act Density 0.006%

    No Known Activations