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

    Neuronpedia

    INDEX
    Explanations

    approval/popularity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lope
    -0.07
     manifesto
    -0.07
     вимог
    -0.06
     Kun
    -0.06
     Path
    -0.06
     Pen
    -0.06
    ibr
    -0.06
     Capacity
    -0.06
     remarks
    -0.06
    ukes
    -0.06
    POSITIVE LOGITS
     werk
    0.06
     تجاری
    0.06
    _blk
    0.06
    .extend
    0.06
    =logging
    0.06
    metics
    0.06
     вигля
    0.06
    ind
    0.06
    DMA
    0.06
    (parcel
    0.06
    Act Density 0.004%

    No Known Activations