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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inquiry or questioning

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

    you have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Życiorys
    -0.66
     يتيمه
    -0.62
     useAppContext
    -0.61
    
    -0.55
    SBATCH
    -0.54
    :✨
    -0.53
    ibouti
    -0.51
    DockStyle
    -0.48
    IsPostBack
    -0.47
    MethodManager
    -0.47
    POSITIVE LOGITS
    awang
    0.35
    テンツ
    0.35
    SAC
    0.33
     leve
    0.31
     __(
    0.31
     deaktiviert
    0.31
    Back
    0.30
     limba
    0.30
    chemise
    0.30
     [],
    0.29
    Act Density 0.002%

    No Known Activations