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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on numeric values (including decimals and figure/table references) in technical text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (MainActivity
    -0.07
     mins
    -0.06
    (left
    -0.06
    “Yes
    -0.06
    Destination
    -0.06
    -wall
    -0.06
    Grid
    -0.06
    agrid
    -0.06
    023
    -0.06
     tsl
    -0.06
    POSITIVE LOGITS
     حکوم
    0.07
     FormBuilder
    0.06
    )$_
    0.06
     dấu
    0.06
     subset
    0.06
    cnt
    0.06
     vaguely
    0.06
     Nationwide
    0.06
     adequ
    0.06
     facto
    0.06
    Act Density 0.054%

    No Known Activations