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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dried
    -0.07
     Remaining
    -0.07
     burada
    -0.07
     вз
    -0.06
    way
    -0.06
    ündeki
    -0.06
    っき
    -0.06
    aja
    -0.06
    規
    -0.06
    hua
    -0.06
    POSITIVE LOGITS
     rivalry
    0.08
    |=↵
    0.06
    <link
    0.06
    :SetPoint
    0.06
     ridiculously
    0.06
     accounting
    0.06
     mastur
    0.06
    _wp
    0.06
     Directed
    0.06
     espionage
    0.06
    Act Density 0.001%

    No Known Activations