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

    Neuronpedia

    INDEX
    Explanations

    collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    goo
    -0.07
    .green
    -0.07
    瞅
    -0.07
     WON
    -0.07
    <TSource
    -0.06
    .READ
    -0.06
    cont
    -0.06
    有任何
    -0.06
    igits
    -0.06
    惕
    -0.06
    POSITIVE LOGITS
     lodash
    0.09
     CAM
    0.07
     chromat
    0.07
    (network
    0.07
    "use
    0.07
    Alchemy
    0.07
     Ceremony
    0.06
    Proposal
    0.06
    љ
    0.06
    ℏ
    0.06
    Act Density 0.003%

    No Known Activations