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

    Neuronpedia

    INDEX
    Explanations

    switch

    np_max-act · gemini-2.0-flash

    the presence of hardware control elements such as switches, buttons, or pull-up resistors

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     結
    -0.07
    .Show
    -0.06
    ument
    -0.06
    řaz
    -0.06
    .Record
    -0.06
     จาก
    -0.06
    什么
    -0.06
    .Go
    -0.06
    .Read
    -0.06
    こんに
    -0.06
    POSITIVE LOGITS
     Way
    0.08
    -purpose
    0.06
    Fal
    0.06
     coward
    0.06
     democr
    0.06
    ностей
    0.06
    ward
    0.06
     UF
    0.06
    (parameter
    0.06
    似的
    0.06
    Act Density 0.011%

    No Known Activations