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

    Neuronpedia

    INDEX
    Explanations

    references to data types in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    type assignments or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.68
    RegressionTest
    -0.61
    SaveChangesAsync
    -0.57
    SBATCH
    -0.56
    asteroide
    -0.56
    principalColumn
    -0.53
    genodigd
    -0.52
    --)
    -0.52
     gynhyrchwyd
    -0.51
    ")));
    -0.51
    POSITIVE LOGITS
     type
    1.16
     Type
    1.13
    type
    1.08
     TYPE
    1.05
    Type
    1.05
    getType
    0.96
     types
    0.94
    TYPE
    0.93
    类型
    0.92
     tipo
    0.88
    Act Density 0.116%

    No Known Activations