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

    Neuronpedia

    INDEX
    Explanations

    Code and games

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inki
    -0.57
     Diplomacy
    -0.54
     تضيفلها
    -0.54
    soon
    -0.54
    TintMode
    -0.53
    CHREIBUNG
    -0.51
     Levinson
    -0.51
    Dib
    -0.50
     Hồ
    -0.50
    PathVariable
    -0.49
    POSITIVE LOGITS
    الحياه
    0.63
     transfieras
    0.55
    BufferException
    0.54
     resourceCulture
    0.52
    Rhestr
    0.52
    thâu
    0.50
    WebElementEntity
    0.49
    kháu
    0.48
     يتيمه
    0.47
    bewerken
    0.46
    Act Density 0.001%

    No Known Activations