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

    Neuronpedia

    INDEX
    Explanations

    bar

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “bar” (e.g. in “bar graph,” “bar chart,” or the bar‐plotting function), i.e. references to bar‐style plots.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -0.07
    Find
    -0.06
    оряд
    -0.06
    dyž
    -0.06
     //↵↵
    -0.06
    lish
    -0.06
    _MetadataUsageId
    -0.06
     Rog
    -0.06
    _into
    -0.06
    ειτουργ
    -0.06
    POSITIVE LOGITS
    	token
    0.07
     MACHINE
    0.07
    IFORM
    0.07
    ("|
    0.07
    共和
    0.06
     истории
    0.06
    -install
    0.06
     column
    0.06
     canopy
    0.06
     stanza
    0.06
    Act Density 0.004%

    No Known Activations