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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" in various contexts

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

    "new" keyword followed by a class name

    np_acts-logits-general · gemini-2.0-flash

    instantiating objects or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.59
    évaluateur
    -0.46
     defStyleAttr
    -0.44
     irgend
    -0.44
     AppCompatTheme
    -0.41
    ard
    -0.41
     Füßen
    -0.40
     isNameExpr
    -0.39
     defStyle
    -0.39
     Geschäfte
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    Geplaatst
    0.59
     double
    0.56
     methylene
    0.51
     Nine
    0.49
     Mik
    0.49
     virtual
    0.49
     المعيارى
    0.47
     Mit
    0.47
     Drew
    0.47
    Act Density 0.048%

    No Known Activations