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

    Neuronpedia

    INDEX
    Explanations

    performing very well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TEL
    0.56
    tel
    0.54
    search
    0.49
    global
    0.48
    label
    0.48
    type
    0.48
    config
    0.48
    tu
    0.48
    education
    0.47
    IF
    0.47
    POSITIVE LOGITS
    ќ
    0.43
     Dre
    0.41
     ե
    0.40
     Sailors
    0.40
     Chardonnay
    0.40
    Chase
    0.40
     同时
    0.39
    റൽ
    0.39
    的女
    0.39
     पहनने
    0.39
    Act Density 0.001%

    No Known Activations