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

    Neuronpedia

    INDEX
    Explanations

    watch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     geen
    -0.07
     Cats
    -0.07
    ذر
    -0.07
     fol
    -0.07
     OG
    -0.06
    tracts
    -0.06
     rnd
    -0.06
     géné
    -0.06
     que
    -0.06
     consists
    -0.06
    POSITIVE LOGITS
    indhoven
    0.07
     Akron
    0.06
     Champions
    0.06
    ิตภ
    0.06
    xbb
    0.06
    deniz
    0.06
     xmlhttp
    0.06
    accountId
    0.06
    olland
    0.06
    107
    0.06
    Act Density 0.003%

    No Known Activations