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

    Neuronpedia

    INDEX
    Explanations

    Code characters

    np_max-act · gemini-2.0-flash

    This neuron responds to statement terminators in code—tokens like “);” or “};” that mark the end of a statement.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Cr
    -0.08
     CONF
    -0.07
     нав
    -0.07
     hver
    -0.06
     Fac
    -0.06
    _INITIALIZER
    -0.06
     SAL
    -0.06
     Ide
    -0.06
     Sequ
    -0.06
     slave
    -0.06
    POSITIVE LOGITS
     differing
    0.07
    Mounted
    0.07
     onComplete
    0.06
     Mourinho
    0.06
    ipop
    0.06
    Looper
    0.06
    acomment
    0.06
     %>
    0.06
    마사지
    0.06
    minent
    0.06
    Act Density 0.062%

    No Known Activations