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

    Neuronpedia

    INDEX
    Explanations

    images

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autom
    -0.08
     original
    -0.07
     fee
    -0.07
    _comp
    -0.06
     phí
    -0.06
    Final
    -0.06
     dostate
    -0.06
    coon
    -0.06
    (original
    -0.06
    968
    -0.06
    POSITIVE LOGITS
    .FindAsync
    0.07
    .getDay
    0.06
    好了
    0.06
     Valent
    0.06
     PAT
    0.06
    рещ
    0.06
    perienced
    0.06
    圣
    0.06
     ART
    0.06
    されて
    0.06
    Act Density 0.008%

    No Known Activations