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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UBLE
    -0.07
    ceb
    -0.06
     })
↵
↵
    -0.06
     pubs
    -0.06
    Toolkit
    -0.06
    redd
    -0.06
    ion
    -0.06
     jeux
    -0.06
    결
    -0.06
    ินเด
    -0.06
    POSITIVE LOGITS
     which
    0.07
     Detailed
    0.07
     davon
    0.07
    .documentation
    0.07
    pictures
    0.07
     которого
    0.06
    ปกครอง
    0.06
     hely
    0.06
     allegation
    0.06
     onViewCreated
    0.06
    Act Density 0.006%

    No Known Activations