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

    Neuronpedia

    INDEX
    Explanations

    technical abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ろ
    -0.06
    -neutral
    -0.06
     live
    -0.06
     لس
    -0.06
     ninth
    -0.06
     hypocrisy
    -0.06
     Styled
    -0.06
    /tool
    -0.06
     sincerely
    -0.06
     Encrypt
    -0.06
    POSITIVE LOGITS
     midfielder
    0.07
    )')↵
    0.07
    astype
    0.06
    ghan
    0.06
    _val
    0.06
    ения
    0.06
    __()↵
    0.06
    .println
    0.06
    ipment
    0.06
    -values
    0.06
    Act Density 0.000%

    No Known Activations