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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of signing or signed formal agreements, treaties, or contracts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Map
    -0.07
     oracle
    -0.07
     Trees
    -0.07
     TREE
    -0.07
     attractions
    -0.07
     heater
    -0.07
    East
    -0.07
     GLenum
    -0.07
     Tree
    -0.07
    Park
    -0.06
    POSITIVE LOGITS
     signed
    0.13
     signing
    0.11
    signed
    0.10
    Signed
    0.09
     Signed
    0.09
    -signed
    0.09
    Signing
    0.09
     Signing
    0.09
     signings
    0.08
    Signature
    0.07
    Act Density 0.015%

    No Known Activations