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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements and structures used in programming

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

    internal method or variable identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.71
    AddTagHelper
    -0.67
     CreateTagHelper
    -0.66
    IUrlHelper
    -0.59
    évaluateur
    -0.56
     oprot
    -0.50
    WaitGroup
    -0.50
    IsMutable
    -0.50
    IVEREF
    -0.48
    IntoConstraints
    -0.48
    POSITIVE LOGITS
     _
    0.59
     (_
    0.54
    ]._
    0.53
    =_
    0.53
     [_
    0.52
     ._
    0.50
    >(_
    0.50
     (!_
    0.48
    (_
    0.47
     '_
    0.47
    Act Density 0.035%

    No Known Activations