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

    Neuronpedia

    INDEX
    Explanations

    skill development

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric tokens (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Zoo
    -0.07
    Queryable
    -0.07
     %>
    -0.07
     mơ
    -0.06
     Mata
    -0.06
    orges
    -0.06
     conclus
    -0.06
    astics
    -0.06
     spectra
    -0.06
     정부
    -0.06
    POSITIVE LOGITS
     ItemStack
    0.07
     developed
    0.07
    _rewards
    0.06
    _trade
    0.06
    форм
    0.06
     adjust
    0.06
    rop
    0.06
    戶
    0.06
    chlor
    0.06
    gere
    0.06
    Act Density 0.071%

    No Known Activations