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

    Neuronpedia

    INDEX
    Explanations

    sim

    np_max-act · gemini-2.0-flash

    This neuron detects LaTeX “\sim” tokens that introduce approximate numeric values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pantry
    -0.08
    ez
    -0.07
    uche
    -0.07
    	cnt
    -0.07
    LU
    -0.06
     todas
    -0.06
    �
    -0.06
     conveniently
    -0.06
    ancial
    -0.06
    _multi
    -0.06
    POSITIVE LOGITS
    .datatables
    0.07
     neo
    0.06
     lbl
    0.06
    .Description
    0.06
    mol
    0.06
    !==
    0.06
    promise
    0.06
    IndexPath
    0.06
    (/
    0.06
     ≠
    0.06
    Act Density 0.003%

    No Known Activations