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

    Neuronpedia

    INDEX
    Explanations

    code constructs related to conditions and branching logic

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

    Case statements or possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.48
    <eos>
    -0.40
     emp
    -0.36
    뀔
    -0.35
    Bibliographie
    -0.34
     policiers
    -0.33
     driven
    -0.33
     worden
    -0.32
     fédé
    -0.32
     or
    -0.32
    POSITIVE LOGITS
    oa̍t
    0.68
     Савезне
    0.66
    fjspx
    0.66
    帖最后由
    0.64
     ***!
    0.64
    SharedDtor
    0.64
    RegressionTest
    0.63
    BufferException
    0.63
     كومونز
    0.60
    tagPool
    0.59
    Act Density 0.048%

    No Known Activations