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

    Neuronpedia

    INDEX
    Explanations

    movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAMAGES
    -0.06
    eut
    -0.06
    訳
    -0.06
    _track
    -0.06
     инфек
    -0.06
    .sig
    -0.06
    Outputs
    -0.06
    extras
    -0.06
     Πα
    -0.06
    /downloads
    -0.06
    POSITIVE LOGITS
    ylene
    0.07
     {//
    0.07
     curvature
    0.07
    档
    0.07
    Roy
    0.06
     hissed
    0.06
     Roy
    0.06
    ři
    0.06
    thane
    0.06
    byter
    0.06
    Act Density 0.009%

    No Known Activations