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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and declarations in programming context

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

    mathematical variables or code tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.90
    aarrggbb
    -0.81
    DockStyle
    -0.77
     snippetHide
    -0.75
    InjectAttribute
    -0.73
    ðsíða
    -0.72
     AssemblyCulture
    -0.72
     メンテナ
    -0.71
    niſſe
    -0.71
     témoig
    -0.71
    POSITIVE LOGITS
     п
    0.30
    bel
    0.30
    PA
    0.29
     su
    0.29
     equi
    0.28
     
    0.28
    DET
    0.28
    su
    0.27
    BEL
    0.27
     mer
    0.26
    Act Density 0.021%

    No Known Activations