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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    盒
    -0.07
     техніч
    -0.06
    .We
    -0.06
     ZX
    -0.06
     Buffered
    -0.06
    BOX
    -0.06
     Dem
    -0.06
    <size
    -0.06
     harvesting
    -0.06
     drinking
    -0.06
    POSITIVE LOGITS
    atum
    0.07
     đ
    0.06
     ActiveRecord
    0.06
    ращения
    0.06
    sin
    0.06
     Getty
    0.06
     quam
    0.06
    dash
    0.06
    ِل
    0.06
     Spear
    0.06
    Act Density 0.016%

    No Known Activations