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

    Neuronpedia

    INDEX
    Explanations

    words commonly used in mathematical or physics papers

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.63
    astify
    -0.63
    ArrowToggle
    -0.63
    setVerticalGroup
    -0.57
    ########.
    -0.54
     JpaRepository
    -0.51
    abank
    -0.50
     fusca
    -0.50
    velocityY
    -0.49
     habitudes
    -0.49
    POSITIVE LOGITS
    исленность
    0.56
    CodedInputStream
    0.52
     Kirkland
    0.49
     un
    0.48
    יצד
    0.48
     bursting
    0.48
     convince
    0.46
    arie
    0.45
     stret
    0.44
     Come
    0.44
    Act Density 40.882%

    No Known Activations