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

    Neuronpedia

    INDEX
    Explanations

    instances of rejection or dismissal in the context of a list or set of criteria

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

    rejected or intermediate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     algemene
    -0.48
     surla
    -0.47
     مُعرِّف
    -0.47
     prochains
    -0.45
     Chriftian
    -0.44
     própri
    -0.44
     supplementary
    -0.43
    NumberOf
    -0.42
    Aiheesta
    -0.42
     menjadikan
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.56
    ViewInit
    0.53
    astéroïdes
    0.52
    iNdEx
    0.45
    RTSN
    0.44
    TargetException
    0.44
    LLocation
    0.43
     AssemblyCompany
    0.43
    CloseOperation
    0.43
    tagHelperRunner
    0.41
    Act Density 0.442%

    No Known Activations