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

    Neuronpedia

    INDEX
    Explanations

    numerical relations, increases, and deletions in scientific results

    oai_token-act-pair · gemini-2.0-flash

    mathematical increase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RunWith
    -0.57
     rosette
    -0.54
     GoogleFonts
    -0.52
    viser
    -0.52
     متعلقه
    -0.52
    WEBPACK
    -0.51
     Cambo
    -0.51
     infractions
    -0.50
    Kaieteur
    -0.50
     imig
    -0.49
    POSITIVE LOGITS
    asteroide
    0.52
     counter
    0.51
    counter
    0.50
    findpost
    0.50
    fillType
    0.46
    árol
    0.45
     vers
    0.45
     становника
    0.44
    tadiene
    0.42
    ftagPool
    0.42
    Act Density 1.394%

    No Known Activations