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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric constants in equations—specifically floating‐point literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,is
    -0.06
    σεις
    -0.06
     voi
    -0.06
    rut
    -0.06
     Conse
    -0.06
     novel
    -0.06
     relevance
    -0.06
    mittel
    -0.06
    ck
    -0.06
     gói
    -0.06
    POSITIVE LOGITS
    (enemy
    0.07
     Increases
    0.07
     bilateral
    0.07
    HashSet
    0.06
     перел
    0.06
    �
    0.06
    lesen
    0.06
     RequestContext
    0.06
    oding
    0.06
     reopening
    0.06
    Act Density 0.007%

    No Known Activations