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

    Neuronpedia

    INDEX
    Explanations

    negative or negating expressions

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

    foreign and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonatomic
    -0.50
    Clik
    -0.47
    findpost
    -0.45
     NgModule
    -0.40
    SBATCH
    -0.40
    CppMethod
    -0.39
    MessageTagHelper
    -0.38
    VersionUID
    -0.36
    IBOutlet
    -0.36
     NSCoder
    -0.35
    POSITIVE LOGITS
    uxxxx
    0.65
     BRARY
    0.58
    ніципалі
    0.57
    BibitemShut
    0.55
     IBRARY
    0.54
    arangay
    0.53
    glises
    0.53
    ſammen
    0.52
    Tikang
    0.52
     Wikimedijinoj
    0.52
    Act Density 0.002%

    No Known Activations