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

    Neuronpedia

    INDEX
    Explanations

    _weight

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric dimension and weight values in Android XML (e.g. dp sizes and layout_weight numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    верд
    -0.07
     FirebaseDatabase
    -0.07
     UserProfile
    -0.07
     upper
    -0.06
     XIII
    -0.06
     Vous
    -0.06
    OWL
    -0.06
    \Domain
    -0.06
    TimeInterval
    -0.06
     reception
    -0.06
    POSITIVE LOGITS
    -document
    0.07
     ser
    0.06
     impover
    0.06
    lightly
    0.06
    could
    0.06
    miss
    0.06
     розроб
    0.06
     heated
    0.06
    _routes
    0.06
     patří
    0.06
    Act Density 0.001%

    No Known Activations