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

    Neuronpedia

    INDEX
    Explanations

    general

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chat
    -0.06
     tat
    -0.06
     комнат
    -0.06
    _CONNECT
    -0.06
     حف
    -0.06
    (proj
    -0.06
    Τα
    -0.06
    (',')[
    -0.06
    _kwargs
    -0.06
    以
    -0.06
    POSITIVE LOGITS
     Person
    0.07
     general
    0.07
    General
    0.07
    .APPLICATION
    0.06
     hoàng
    0.06
    .full
    0.06
     commonly
    0.06
    (angle
    0.06
     пояс
    0.06
    Required
    0.06
    Act Density 0.005%

    No Known Activations