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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron responds to floating‐point numeric literals (decimal numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Felipe
    -0.06
     recurrence
    -0.06
    igrants
    -0.06
     homemade
    -0.06
    abric
    -0.06
    (validation
    -0.06
     Rohingya
    -0.06
    anager
    -0.06
     plunged
    -0.06
    American
    -0.06
    POSITIVE LOGITS
    fully
    0.07
    사
    0.07
     Indy
    0.07
     lockdown
    0.06
    说道
    0.06
    cosa
    0.06
    ').'</
    0.06
    裏
    0.06
    백
    0.06
     những
    0.06
    Act Density 0.003%

    No Known Activations