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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pdata
    -0.07
    <E
    -0.07
    freq
    -0.07
     quer
    -0.06
     provoc
    -0.06
    /main
    -0.06
     Presented
    -0.06
    significant
    -0.06
    HI
    -0.06
    、彼
    -0.06
    POSITIVE LOGITS
     сем
    0.07
     whilst
    0.06
    OMPI
    0.06
     ease
    0.06
     комплекс
    0.06
    urchases
    0.05
    аб
    0.05
    obar
    0.05
    บาล
    0.05
     Hermes
    0.05
    Act Density 0.000%

    No Known Activations