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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and their related phrases

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

    introduces explanations or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.55
    ragalactic
    -0.54
    styleType
    -0.54
    SBATCH
    -0.50
    ndry
    -0.50
    Trichloroethane
    -0.49
     Pardavimas
    -0.49
     الرياضيه
    -0.49
    ロウィン
    -0.49
    othelioma
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.37
    Lähteet
    0.36
    RefNanny
    0.33
     getattr
    0.33
     Yeah
    0.32
     yes
    0.32
    testify
    0.31
    webElementXpaths
    0.31
    पया
    0.29
    yes
    0.28
    Act Density 0.001%

    No Known Activations