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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act · gemini-2.0-flash

    The neuron activates on explicit mentions of hyperlinks or external URLs (e.g. “links,” “websites,” “https://,” “videos”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _RS
    -0.08
    ůl
    -0.07
    iset
    -0.06
     Decide
    -0.06
    資
    -0.06
    abstractmethod
    -0.06
    sil
    -0.06
    이라고
    -0.06
    actical
    -0.05
    造
    -0.05
    POSITIVE LOGITS
    İng
    0.08
     QSql
    0.08
     Initializes
    0.08
     Colors
    0.07
     dns
    0.07
     RaycastHit
    0.07
    :SetPoint
    0.07
     Tories
    0.07
     HRESULT
    0.07
    (!_
    0.07
    Act Density 0.011%

    No Known Activations