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

    Neuronpedia

    INDEX
    Explanations

    data type specifications and method declarations in programming contexts

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

    String manipulation and object properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Promises
    -0.43
    JOUR
    -0.42
    ItemGroup
    -0.42
     Ahnung
    -0.42
    yntaxException
    -0.42
    徒
    -0.42
    eseorang
    -0.41
    pilar
    -0.41
    󠁮
    -0.41
     fewest
    -0.40
    POSITIVE LOGITS
     skall
    0.56
     Whilst
    0.56
    ExtendWith
    0.55
     allAfrica
    0.54
    faßt
    0.54
    -------
    0.53
     whilst
    0.52
    Whilst
    0.51
     Miß
    0.50
    uxxxx
    0.49
    Act Density 0.030%

    No Known Activations