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

    Neuronpedia

    INDEX
    Explanations

    display names and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yns
    -0.99
    randomUUID
    -0.85
    quini
    -0.77
    chede
    -0.74
    日期
    -0.73
    襪
    -0.73
    を参照
    -0.72
    DATE
    -0.72
     colorWith
    -0.71
    Einzelnachweise
    -0.71
    POSITIVE LOGITS
     display
    2.48
    DisplayName
    2.38
     label
    2.20
     displayName
    2.20
    displayName
    2.19
     Display
    2.17
    display
    2.11
     name
    2.09
     human
    1.98
    DISPLAY
    1.88
    Act Density 0.119%

    No Known Activations