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

    Neuronpedia

    INDEX
    Explanations

    terms related to regulations, methodologies, and findings in research contexts

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

    specific topics and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.40
     alinea
    -0.37
     wireType
    -0.36
    getFile
    -0.36
     þat
    -0.35
    Publishers
    -0.35
     combinaison
    -0.34
     ciascuno
    -0.34
     colgantes
    -0.34
    ソッド
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.62
    0.57
    ViewFeatures
    0.56
    Tikang
    0.56
     Baillargeon
    0.52
     efforts
    0.52
    AnchorStyles
    0.51
    ViewInit
    0.50
     proceedings
    0.49
     BrowserModule
    0.49
    Act Density 0.127%

    No Known Activations