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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—particularly digits and decimal numbers in procedural or measurement contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,left
    -0.07
    force
    -0.06
    ecycle
    -0.06
     setback
    -0.06
    .KeyEvent
    -0.06
     translation
    -0.06
     동안
    -0.05
    počet
    -0.05
    EEEE
    -0.05
    FORCE
    -0.05
    POSITIVE LOGITS
     zorun
    0.07
     nhuận
    0.07
    บ
    0.07
     numberWithInt
    0.07
     vů
    0.07
    sub
    0.06
    .unregister
    0.06
    uC
    0.06
     Blog
    0.06
     ‎#
    0.06
    Act Density 0.019%

    No Known Activations