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

    Neuronpedia

    INDEX
    Explanations

    .html

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “.html,” i.e. it detects the “.html” file‐extension substring.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .StObject
    -0.07
    agedList
    -0.06
     Lud
    -0.06
    anca
    -0.06
     Jud
    -0.06
     Rand
    -0.06
    WebService
    -0.06
    .canvas
    -0.06
    contracts
    -0.06
    .bc
    -0.06
    POSITIVE LOGITS
     *,
    0.06
     ohled
    0.06
     depois
    0.06
     several
    0.06
    -ng
    0.06
     Throwable
    0.06
    VERY
    0.06
    uminum
    0.06
     blanket
    0.06
     Lith
    0.06
    Act Density 0.005%

    No Known Activations