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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to notable achievements and records

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

    first time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.41
     Fit
    -0.33
     FIT
    -0.33
    Бахар
    -0.32
    ModelAndView
    -0.32
    XmlAccessorType
    -0.31
    AddHtmlAttribute
    -0.31
     Top
    -0.31
     zda
    -0.30
     saída
    -0.29
    POSITIVE LOGITS
     ProtoMessage
    0.65
     AssemblyCulture
    0.57
    fromnode
    0.52
     Taktlose
    0.52
    zij
    0.51
    endphp
    0.50
    stateProvider
    0.50
     gynhyrchwyd
    0.50
    nalités
    0.49
    Havolalar
    0.49
    Act Density 0.108%

    No Known Activations