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

    Neuronpedia

    INDEX
    Explanations

    Rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reli
    -0.09
     Reliable
    -0.08
     lyd
    -0.08
    可靠
    -0.08
    Reli
    -0.08
     اینترنت
    -0.08
     artiste
    -0.08
     Reliability
    -0.08
    Reliable
    -0.07
     dependable
    -0.07
    POSITIVE LOGITS
     twisting
    0.12
    .rotation
    0.11
    .rotate
    0.11
     torso
    0.11
     Twist
    0.11
     twist
    0.10
     twists
    0.10
     rotates
    0.10
     rotation
    0.10
     rotating
    0.10
    Act Density 0.007%

    No Known Activations