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

    Neuronpedia

    INDEX
    Explanations

    <<

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ामन
    -0.07
    ius
    -0.07
    125
    -0.07
    �
    -0.06
    ิลล
    -0.06
    ]("
    -0.06
    Wrong
    -0.06
    _CL
    -0.06
    ِين
    -0.06
    man
    -0.06
    POSITIVE LOGITS
    중에
    0.08
    "<<
    0.07
    بال
    0.07
    grab
    0.07
     picturesque
    0.07
    lycer
    0.07
     metam
    0.07
     Cherry
    0.07
     BeautifulSoup
    0.06
     <<
    0.06
    Act Density 0.008%

    No Known Activations