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

    Neuronpedia

    INDEX
    Explanations

    code descriptions and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     U
    0.50
    S
    0.48
     S
    0.47
     M
    0.46
    max
    0.44
    ulating
    0.44
    U
    0.44
     Calculate
    0.43
    v
    0.43
     Amount
    0.43
    POSITIVE LOGITS
     rối
    0.52
    вят
    0.47
    getDescription
    0.46
    ியுடன்
    0.46
    श्च
    0.46
    ו
    0.45
     Descriptions
    0.45
     possessed
    0.45
     disagreeable
    0.43
     sustains
    0.42
    Act Density 0.001%

    No Known Activations