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

    Neuronpedia

    INDEX
    Explanations

    ipped skip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лаш
    -0.06
     challeng
    -0.06
    wolf
    -0.06
     mentoring
    -0.06
    848
    -0.06
    _shapes
    -0.06
    ्रण
    -0.06
    Outputs
    -0.06
    ない
    -0.06
    adel
    -0.06
    POSITIVE LOGITS
    PHY
    0.07
    (un
    0.06
     случаях
    0.06
     kamp
    0.06
     │
    0.06
    stagram
    0.06
     Unt
    0.06
     홈
    0.06
     misrepresented
    0.06
     BuzzFeed
    0.06
    Act Density 0.006%

    No Known Activations