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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparison and evaluation

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

    comparison error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viewDidLoad
    -0.52
    calientes
    -0.47
    xAA
    -0.45
     Penh
    -0.43
    tshell
    -0.42
    lastonbury
    -0.42
    cury
    -0.41
    Pike
    -0.41
     uș
    -0.40
    letic
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.60
     rechange
    0.43
     autorytatywna
    0.42
    IUrlHelper
    0.40
    bereit
    0.39
    
    0.38
    رشف
    0.38
     rappro
    0.37
    Tikang
    0.37
    HasColumnType
    0.36
    Act Density 0.022%

    No Known Activations