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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     перевір
    -0.08
    /simple
    -0.07
    /count
    -0.07
    marginLeft
    -0.06
    [counter
    -0.06
    걸
    -0.06
    Fatal
    -0.06
     Demp
    -0.06
    訪
    -0.06
    ああ
    -0.06
    POSITIVE LOGITS
     intra
    0.07
    -native
    0.07
    .jpeg
    0.06
    ัณฑ
    0.06
     ром
    0.06
    istration
    0.06
    ersh
    0.06
    оф
    0.06
     SV
    0.06
    YGON
    0.06
    Act Density 0.012%

    No Known Activations