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

    Neuronpedia

    INDEX
    Explanations

    FILE

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the all-caps “THIS FILE IS GENERATED…” boilerplate comment lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.07
     gridSize
    -0.07
    είς
    -0.06
    RING
    -0.06
    .Series
    -0.06
    Activity
    -0.06
    ΑΝΤ
    -0.06
    cdb
    -0.06
     गई
    -0.06
    fad
    -0.05
    POSITIVE LOGITS
     Correspond
    0.08
     COR
    0.07
     직
    0.07
     don
    0.07
     anyone
    0.07
     won
    0.07
     visually
    0.06
     Icon
    0.06
     Dual
    0.06
     resolving
    0.06
    Act Density 0.002%

    No Known Activations