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

    Neuronpedia

    INDEX
    Explanations

    exercise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     switch
    -0.08
    ItemSelected
    -0.07
    preferences
    -0.07
    BG
    -0.07
     IDS
    -0.07
    _keywords
    -0.07
    _SIDE
    -0.07
    一期
    -0.07
     Canter
    -0.07
    资助
    -0.07
    POSITIVE LOGITS
    	NdrFc
    0.08
    촤
    0.07
    ጃ
    0.07
     truthful
    0.07
    תיאור
    0.06
    珖
    0.06
    폈
    0.06
     Dur
    0.06
    _histogram
    0.06
    澡
    0.06
    Act Density 0.099%

    No Known Activations