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

    Neuronpedia

    INDEX
    Explanations

    information extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "d
    -0.07
    .indent
    -0.07
    onavir
    -0.06
    ิล
    -0.06
    Interpolator
    -0.06
     cầm
    -0.06
     Fus
    -0.06
     snowy
    -0.06
     Seq
    -0.06
     circumference
    -0.06
    POSITIVE LOGITS
     dj
    0.07
     worker
    0.06
     Innoc
    0.06
     opport
    0.06
     percentages
    0.06
     desks
    0.06
     Decor
    0.06
     Thermal
    0.06
     σχ
    0.06
     eng
    0.06
    Act Density 0.050%

    No Known Activations