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

    Neuronpedia

    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash

    The neuron flags decimal-formatted numerical values (floating-point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     featuring
    -0.07
    SAMPLE
    -0.07
     mask
    -0.07
    فاده
    -0.06
     tabs
    -0.06
    для
    -0.06
    agit
    -0.06
    INGLE
    -0.06
    Developer
    -0.06
    >w
    -0.06
    POSITIVE LOGITS
     dưới
    0.07
     enh
    0.07
    uristic
    0.06
     Comple
    0.06
    lâm
    0.06
     Danielle
    0.06
     IsPlainOldData
    0.06
     생활
    0.06
     xây
    0.06
    .setMaximum
    0.06
    Act Density 0.047%

    No Known Activations