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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aret
    -0.08
     Find
    -0.07
    ưng
    -0.07
    nier
    -0.07
     paranoid
    -0.07
    /provider
    -0.06
    unque
    -0.06
    _Get
    -0.06
    妥
    -0.06
    aver
    -0.06
    POSITIVE LOGITS
    疏导
    0.08
     obligations
    0.08
     trucks
    0.08
     grad
    0.07
    が始ま
    0.07
     velocities
    0.07
    .pay
    0.07
    .multiply
    0.07
    _integral
    0.07
     или
    0.07
    Act Density 0.005%

    No Known Activations