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

    Neuronpedia

    INDEX
    Explanations

    angle brackets

    np_max-act · gemini-2.0-flash

    The neuron detects LaTeX commands that introduce or close mathematical delimiters (e.g. “\lbrace”, “\rbrace”, “\langle”, “\rangle”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    医
    -0.08
    01
    -0.07
    0
    -0.07
    _VISIBLE
    -0.07
    00
    -0.07
    )">
    -0.07
    03
    -0.07
    show
    -0.06
    !»
    -0.06
     Fucking
    -0.06
    POSITIVE LOGITS
    	rep
    0.08
    �
    0.07
    bare
    0.07
    .par
    0.07
    pter
    0.07
    brand
    0.07
     Straight
    0.07
    лугов
    0.06
     Plat
    0.06
     hart
    0.06
    Act Density 0.007%

    No Known Activations