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

    Neuronpedia

    INDEX
    Explanations

    declarations and identifiers in programming code

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

    From there,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.89
     transfieras
    -0.87
     surla
    -0.81
     snippetHide
    -0.81
     <<<<<<<<<<<<<<
    -0.79
     мәкал
    -0.78
     queſta
    -0.75
    endphp
    -0.72
    ValueStyle
    -0.72
     שוליים
    -0.72
    POSITIVE LOGITS
    Autowired
    0.69
    ,
    0.40
     also
    0.39
    Override
    0.38
    ↵
    0.34
    ↵↵
    0.34
     $
    0.32
     renon
    0.32
     
    0.31
    :
    0.30
    Act Density 0.000%

    No Known Activations