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

    Neuronpedia

    INDEX
    Explanations

    npm init -y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ActionButton
    0.43
    CLion
    0.40
    popupButton
    0.39
    延長
    0.39
    レビ
    0.38
    സ്ട
    0.38
     gating
    0.38
     tablespoon
    0.37
     AVLNode
    0.37
     Hillsborough
    0.37
    POSITIVE LOGITS
     Inicial
    0.67
     Init
    0.64
    Init
    0.60
    Inicial
    0.60
     init
    0.57
    init
    0.57
     inicial
    0.57
     iniz
    0.56
     Initialization
    0.55
    inicial
    0.54
    Act Density 0.003%

    No Known Activations