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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urrection
    -0.07
    acula
    -0.07
    many
    -0.06
    itch
    -0.06
    death
    -0.06
    abet
    -0.06
    ycles
    -0.06
     ;↵↵
    -0.06
    ewe
    -0.06
    aos
    -0.06
    POSITIVE LOGITS
     liner
    0.08
    -dat
    0.07
     circ
    0.07
     cer
    0.07
    (mm
    0.07
     lined
    0.06
     devastated
    0.06
     Lincoln
    0.06
     mô
    0.06
    ilage
    0.06
    Act Density 0.004%

    No Known Activations