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

    Neuronpedia

    INDEX
    Explanations

    phone recordings and messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domination
    -0.08
     fertil
    -0.08
    (Window
    -0.08
     możemy
    -0.08
     abstraction
    -0.08
     morphology
    -0.07
     FED
    -0.07
     financi
    -0.07
     financement
    -0.07
     नाव
    -0.07
    POSITIVE LOGITS
     concierge
    0.10
     Concierge
    0.10
     маршру
    0.09
     visitantes
    0.09
     triggered
    0.09
    welcome
    0.09
     Visitors
    0.09
     prerecorded
    0.09
     traps
    0.09
    Bienvenue
    0.09
    Act Density 0.036%

    No Known Activations