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

    Neuronpedia

    INDEX
    Explanations

    Grammatical sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incarceration
    -0.06
    eliness
    -0.06
    ]()↵
    -0.06
     Kết
    -0.06
    -helper
    -0.06
    /test
    -0.06
    oise
    -0.06
     lesbians
    -0.06
    _icon
    -0.06
    _MARKER
    -0.06
    POSITIVE LOGITS
     Assertion
    0.07
     Г
    0.07
    _DIRECTORY
    0.06
     ฟร
    0.06
     iv
    0.06
     математи
    0.06
    	cs
    0.06
    _CODES
    0.06
     few
    0.06
     Coch
    0.06
    Act Density 0.056%

    No Known Activations