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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literal tokens (especially floating-point and hex numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .books
    -0.07
     Cher
    -0.07
    AG
    -0.06
    ipro
    -0.06
     Span
    -0.06
    /)
    -0.06
     Alaska
    -0.06
    ुण
    -0.06
     knockout
    -0.06
     polite
    -0.06
    POSITIVE LOGITS
     모든
    0.07
     hotline
    0.06
     اهم
    0.06
     vip
    0.06
    ebiliriz
    0.06
     ще
    0.06
    .lastName
    0.06
    _no
    0.06
    incl
    0.06
    .TypeOf
    0.06
    Act Density 0.031%

    No Known Activations