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

    Neuronpedia

    INDEX
    Explanations

    syntax elements related to programming and data structure manipulation

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

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.76
    IVEREF
    -0.67
     ujednoznacz
    -0.63
    expandindo
    -0.63
    AsUp
    -0.62
     defaultstate
    -0.59
    RTEE
    -0.57
    kloped
    -0.56
    msgTypes
    -0.54
    Хьажоргаш
    -0.53
    POSITIVE LOGITS
     виправивши
    0.54
     ervan
    0.38
    <eos>
    0.38
    abend
    0.38
    setCellStyle
    0.34
     may
    0.33
    PDOException
    0.33
     Claude
    0.33
     hands
    0.33
    pecha
    0.33
    Act Density 0.009%

    No Known Activations