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

    Neuronpedia

    INDEX
    Explanations

    Find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flushing
    -0.07
    FileType
    -0.07
    .lp
    -0.07
    Updating
    -0.07
    LA
    -0.07
     Zinc
    -0.06
     уров
    -0.06
    981
    -0.06
    blo
    -0.06
    .Look
    -0.06
    POSITIVE LOGITS
    において
    0.07
     unrest
    0.07
    рев
    0.06
    _workers
    0.06
    vement
    0.06
    _scaling
    0.06
    dou
    0.06
    揮
    0.06
    닝
    0.06
     Sp
    0.06
    Act Density 0.012%

    No Known Activations