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

    Neuronpedia

    INDEX
    Explanations

    code constructs and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     df
    0.42
     प्रश्नावली
    0.42
    GBuf
    0.40
     DF
    0.38
    df
    0.37
    InstanceOf
    0.37
     McAfee
    0.37
     คณิต
    0.36
     DFT
    0.36
     Scro
    0.36
    POSITIVE LOGITS
    ზ
    0.44
    chill
    0.42
    }\,
    0.41
    jeta
    0.40
    changer
    0.40
     ზ
    0.38
     यूएस
    0.38
     иденти
    0.38
    िक
    0.37
    年初
    0.37
    Act Density 1.776%

    No Known Activations