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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal‐formatted numeric values (fractions or percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    arus
    -0.08
    :item
    -0.07
     스포츠
    -0.07
    CLUDE
    -0.06
     EDT
    -0.06
    isia
    -0.06
    \Queue
    -0.06
    omidou
    -0.06
     critics
    -0.06
    _("
    -0.06
    POSITIVE LOGITS
     infrastructure
    0.06
     obedience
    0.06
     discreet
    0.06
     mux
    0.06
     Darling
    0.06
     подс
    0.06
    natal
    0.05
    .Cell
    0.05
    申请
    0.05
    .ndim
    0.05
    Act Density 0.004%

    No Known Activations