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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ActivityIndicatorView
    -0.08
    brick
    -0.07
     وذلك
    -0.07
    weight
    -0.07
    abs
    -0.07
    -Day
    -0.06
    collapsed
    -0.06
     DLL
    -0.06
    осп
    -0.06
     enthusiastic
    -0.06
    POSITIVE LOGITS
    acidad
    0.07
    _iface
    0.07
     +
↵
    0.07
    нт
    0.06
     profoundly
    0.06
     hw
    0.06
    ..↵↵↵↵
    0.06
     груз
    0.06
    ifix
    0.06
     ди
    0.06
    Act Density 0.000%

    No Known Activations