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

    Neuronpedia

    INDEX
    Explanations

    M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Серг
    -0.07
     Paperback
    -0.07
    .Ge
    -0.07
     đức
    -0.07
    SupportedContent
    -0.07
    ()==
    -0.06
    testdata
    -0.06
     baise
    -0.06
     TPP
    -0.06
    Stan
    -0.06
    POSITIVE LOGITS
     tox
    0.06
    調
    0.06
     строитель
    0.06
     Hip
    0.06
     hop
    0.06
     inj
    0.06
     구매
    0.06
     Latin
    0.06
    ikipedia
    0.06
    (tag
    0.06
    Act Density 0.000%

    No Known Activations