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

    Neuronpedia

    INDEX
    Explanations

    Technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.59
     care
    -0.53
    PhysRev
    -0.50
     مُعرِّف
    -0.50
    Erreferentziak
    -0.49
    Care
    -0.49
     Care
    -0.47
     MenuView
    -0.47
     glo
    -0.46
    варь
    -0.46
    POSITIVE LOGITS
    UserScript
    0.54
     незавершена
    0.52
     Initialized
    0.48
    しくは
    0.48
     amminist
    0.47
     ModelExpression
    0.47
    AndroidJUnit
    0.46
    >>()
    0.46
     merav
    0.45
    lorette
    0.45
    Act Density 0.000%

    No Known Activations