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

    Neuronpedia

    INDEX
    Explanations

    code blocks with indentation

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gla
    -0.57
    ContentAsync
    -0.56
    ])))
    -0.56
     sixth
    -0.55
    geth
    -0.53
     Mini
    -0.52
     eighth
    -0.52
     Saturday
    -0.51
     بيها
    -0.51
     Satur
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.68
    tvguidetime
    0.58
     écoute
    0.56
    ponses
    0.55
     Betracht
    0.55
    riwal
    0.52
     namanya
    0.51
     JpaRepository
    0.49
    ukų
    0.49
    ❸
    0.49
    Act Density 0.284%

    No Known Activations