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

    Neuronpedia

    INDEX
    Explanations

    magnetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بعض
    -0.07
    過
    -0.07
     권
    -0.07
     يأتي
    -0.07
     לטובת
    -0.07
    /of
    -0.07
     butt
    -0.07
     errorMessage
    -0.06
    أتي
    -0.06
     erle
    -0.06
    POSITIVE LOGITS
    威海
    0.08
     Salem
    0.07
    .part
    0.07
     treatments
    0.07
    /foo
    0.07
     semiclassical
    0.07
    -use
    0.07
     hä
    0.07
    reatment
    0.07
    SEA
    0.07
    Act Density 0.005%

    No Known Activations