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

    Neuronpedia

    INDEX
    Explanations

    Rows

    np_max-act · gemini-2.0-flash

    the presence of “Row” or “Rows” substrings in code identifiers (e.g. variable/property names handling table row selection)

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mutlu
    -0.06
     calibration
    -0.06
    StatusCode
    -0.06
    etí
    -0.06
     yeme
    -0.06
    ?>&
    -0.06
     disap
    -0.06
     Vegetable
    -0.06
     inser
    -0.06
     Salv
    -0.06
    POSITIVE LOGITS
    elves
    0.06
     типу
    0.06
    Completion
    0.06
    MemoryWarning
    0.06
    -prev
    0.06
     Clear
    0.06
    240
    0.06
     giorn
    0.06
     Navy
    0.05
     giveaway
    0.05
    Act Density 0.000%

    No Known Activations