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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing decimal or floating-point values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     подаль
    -0.07
     initiatives
    -0.06
    �
    -0.06
    設
    -0.06
     perk
    -0.06
    놓
    -0.06
    intro
    -0.06
    ์ร
    -0.06
     dẫn
    -0.06
    _days
    -0.06
    POSITIVE LOGITS
    罪
    0.07
    ины
    0.06
    Tipo
    0.06
     lim
    0.06
     Brasil
    0.06
    scient
    0.06
    gift
    0.06
    Law
    0.06
     sebagai
    0.06
    .':
    0.06
    Act Density 0.153%

    No Known Activations