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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     specs
    -0.07
     wildly
    -0.06
     assisted
    -0.06
     enjoyable
    -0.06
     Calculation
    -0.06
     arcs
    -0.06
     auto
    -0.06
     complication
    -0.06
     Вс
    -0.06
    -years
    -0.06
    POSITIVE LOGITS
    (piece
    0.07
    heed
    0.07
    olo
    0.06
    iselect
    0.06
    airobi
    0.06
    üph
    0.06
    ubern
    0.06
     graft
    0.06
    .getDouble
    0.06
    owell
    0.06
    Act Density 0.093%

    No Known Activations