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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .rest
    -0.07
     Susp
    -0.07
    奋力
    -0.07
     отдых
    -0.06
    굄
    -0.06
    =pd
    -0.06
    Ǿ
    -0.06
     Rest
    -0.06
     foto
    -0.06
    ።
    -0.06
    POSITIVE LOGITS
    clipboard
    0.07
    ophysical
    0.07
    𝇚
    0.07
     ActionListener
    0.07
    emporary
    0.07
    ROSS
    0.07
    惊人
    0.06
    approved
    0.06
    ional
    0.06
     quickly
    0.06
    Act Density 0.002%

    No Known Activations