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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    This neuron detects calls to “click” (i.e. link‐ or button‐clicking prompts) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Publication
    -0.07
     แหล
    -0.06
    .bad
    -0.06
     probabil
    -0.06
    .Address
    -0.06
     determined
    -0.06
    _ENDPOINT
    -0.06
    CHILD
    -0.06
     promises
    -0.06
    .With
    -0.06
    POSITIVE LOGITS
    *h
    0.07
     هفته
    0.06
    quisite
    0.06
     uvědom
    0.06
     celé
    0.06
    iphers
    0.06
    orative
    0.06
     thermostat
    0.06
    (TR
    0.06
     eig
    0.06
    Act Density 0.004%

    No Known Activations