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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    The neuron flags positive, supportive language—especially compliments and expressions of encouragement or praise.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about relationships and emotional connections.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ้านด
    -0.07
     admired
    -0.06
     слух
    -0.06
     Fuller
    -0.06
     Cork
    -0.06
     men
    -0.06
     subclasses
    -0.06
     enums
    -0.06
     Toledo
    -0.06
    tour
    -0.06
    POSITIVE LOGITS
    hashCode
    0.07
    Abs
    0.07
    ED
    0.07
     imageName
    0.06
    ।
    0.06
    $GLOBALS
    0.06
    ovaná
    0.06
    pixels
    0.06
     treeNode
    0.06
    A
    0.06
    Act Density 0.023%

    No Known Activations