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

    Neuronpedia

    INDEX
    Explanations

    Programming/science questions

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric values with decimal points (e.g. measurements or CAS‐style numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Steak
    -0.06
     DirectX
    -0.06
     moda
    -0.06
    Dup
    -0.06
    olit
    -0.06
     XmlNode
    -0.06
    !!");↵
    -0.06
    _POLICY
    -0.06
     Cleans
    -0.06
    _FONT
    -0.06
    POSITIVE LOGITS
    (timestamp
    0.07
     �
    0.07
     movements
    0.07
    /pr
    0.07
     enrollment
    0.07
     struggles
    0.07
     inclus
    0.07
     справ
    0.07
    	counter
    0.06
     somew
    0.06
    Act Density 0.002%

    No Known Activations