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

    Neuronpedia

    INDEX
    Explanations

    dashes and list markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dictionary
    0.38
    Tools
    0.38
    Grid
    0.37
    Line
    0.36
     tante
    0.36
    வர்களில்
    0.36
    \#
    0.35
    HA
    0.35
    示例
    0.35
    Tool
    0.34
    POSITIVE LOGITS
     flound
    0.47
    𝐭
    0.44
    ǘ
    0.43
     albeit
    0.43
    herjee
    0.42
     SoaException
    0.42
     –,
    0.42
     andRow
    0.41
    齟
    0.41
    including
    0.40
    Act Density 0.000%

    No Known Activations