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

    Neuronpedia

    INDEX
    Explanations

    split

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    departments
    -0.07
    statuses
    -0.06
     DG
    -0.06
    /views
    -0.06
    \\/
    -0.06
    with
    -0.06
    data
    -0.06
    _rc
    -0.06
    (↵↵
    -0.06
    STATIC
    -0.06
    POSITIVE LOGITS
    lico
    0.06
    巨
    0.06
    }")↵
    0.06
     corro
    0.06
    ayscale
    0.06
     궁금
    0.06
    ادية
    0.06
     zombies
    0.06
    Gesture
    0.06
    isel
    0.06
    Act Density 0.006%

    No Known Activations