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

    Neuronpedia

    INDEX
    Explanations

    chatbot training data and evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     በተጨማሪ
    0.78
    CLR
    0.76
     зару
    0.76
     tervez
    0.75
    Autres
    0.75
    develop
    0.73
    Trail
    0.73
     acteur
    0.72
    Resolve
    0.72
    Resolution
    0.71
    POSITIVE LOGITS
    并不
    0.71
    並不
    0.69
     Lamps
    0.68
     berries
    0.67
     lamps
    0.65
     BIS
    0.64
    তথ
    0.64
     helfen
    0.63
    ه
    0.63
    জা
    0.62
    Act Density 0.001%

    No Known Activations