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

    Neuronpedia

    INDEX
    Explanations

    delimiter and formatting symbols in programming text

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

    string concatenation and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.55
    oredCriteria
    -0.55
     ujednoznacz
    -0.55
     ddelweddau
    -0.54
    astéroïdes
    -0.53
     AssemblyTitle
    -0.52
     ModelExpression
    -0.52
    verwijspagina
    -0.52
    rungsseite
    -0.50
    ſelves
    -0.50
    POSITIVE LOGITS
    ChildScrollView
    0.55
     BufferedWriter
    0.51
    readlines
    0.49
     newline
    0.41
    MethodManager
    0.40
    BufferedWriter
    0.39
    StreamWriter
    0.39
     sto
    0.37
    ubmit
    0.37
     flip
    0.36
    Act Density 0.024%

    No Known Activations