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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MORE
    -0.08
    ainter
    -0.08
    हरूले
    -0.07
    人在
    -0.07
    Slip
    -0.07
    _FILL
    -0.07
    ama
    -0.07
     মানুষের
    -0.07
    _DELAY
    -0.07
    -Bahn
    -0.07
    POSITIVE LOGITS
     oversees
    0.09
     overseeing
    0.09
     oversee
    0.09
     overse
    0.08
    ‏
    0.08
     Overse
    0.08
     prest
    0.08
    yos
    0.07
    ுகிறார்
    0.07
     ושל
    0.07
    Act Density 0.248%

    No Known Activations