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

    Neuronpedia

    INDEX
    Explanations

    references to social media or communication platforms

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

    @query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.59
     referrerpolicy
    -0.53
    neys
    -0.51
     Seel
    -0.47
     Krzyż
    -0.47
     Normdatei
    -0.47
     Peker
    -0.46
    ZW
    -0.45
    ControllerAdvice
    -0.45
    PhysRevLett
    -0.45
    POSITIVE LOGITS
    :✨
    0.52
    RepeatedField
    0.50
    IUrlHelper
    0.47
     noDo
    0.44
     ExecuteAsync
    0.43
    󠁴
    0.42
     CanadaChoose
    0.41
    didSet
    0.36
    IndentedString
    0.36
    ➟
    0.35
    Act Density 0.001%

    No Known Activations