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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alist
    -0.07
     Glasgow
    -0.06
    وغ
    -0.06
    AAAAAAAA
    -0.06
    _tw
    -0.06
    _Work
    -0.06
    อส
    -0.06
     Ου
    -0.06
    éry
    -0.06
    otos
    -0.06
    POSITIVE LOGITS
     valves
    0.07
     =>
    0.07
    であり
    0.06
     professional
    0.06
    .Css
    0.06
     The
    0.06
    理
    0.06
    ."""↵
    0.06
    があり
    0.06
    csv
    0.06
    Act Density 0.001%

    No Known Activations