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

    Neuronpedia

    INDEX
    Explanations

    code and game text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    limitations
    -0.08
     acomp
    -0.08
     clarification
    -0.08
     limitations
    -0.08
    ങ്ങനെ
    -0.08
    <!
    -0.08
    confirmation
    -0.07
     cof
    -0.07
    예약
    -0.07
     예약
    -0.07
    POSITIVE LOGITS
    顶部
    0.09
     bottom
    0.09
     heights
    0.09
     transport
    0.09
     bottoms
    0.09
     upward
    0.09
    _bottom
    0.08
     south
    0.08
    _BOTTOM
    0.08
     downward
    0.08
    Act Density 0.005%

    No Known Activations