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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FA
    -0.07
    �
    -0.07
    克
    -0.07
    _paths
    -0.07
     strained
    -0.06
     Morr
    -0.06
     bankers
    -0.06
    .Notification
    -0.06
    _management
    -0.06
    平方公里
    -0.06
    POSITIVE LOGITS
     manufacturer
    0.07
    (show
    0.06
     Benedict
    0.06
    erspective
    0.06
     través
    0.06
     salon
    0.06
    ei
    0.06
     admit
    0.06
    Προ
    0.06
     şeyi
    0.06
    Act Density 0.032%

    No Known Activations