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

    Neuronpedia

    INDEX
    Explanations

    card

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    north
    -0.07
    賽
    -0.07
    不曾
    -0.07
    _inverse
    -0.06
     MessageType
    -0.06
    avi
    -0.06
    输
    -0.06
     Master
    -0.06
    .NORTH
    -0.06
    .after
    -0.06
    POSITIVE LOGITS
    Wunused
    0.08
     зая
    0.08
    *X
    0.07
    MODEL
    0.07
    StateChanged
    0.07
    ;">↵
    0.07
     заявил
    0.07
    äl
    0.07
     Basically
    0.07
    -reviewed
    0.07
    Act Density 0.242%

    No Known Activations