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

    Neuronpedia

    INDEX
    Explanations

    wars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kit
    -0.08
    Seek
    -0.07
     เบ
    -0.07
    -db
    -0.07
    σύ
    -0.06
    +E
    -0.06
    пе
    -0.06
    onor
    -0.06
    Ws
    -0.06
    ứa
    -0.06
    POSITIVE LOGITS
     RL
    0.07
     keywords
    0.07
     WWII
    0.06
    TimeInterval
    0.06
    cluding
    0.06
    ağ
    0.06
     glColor
    0.06
     Farrell
    0.06
    世紀
    0.06
     Offering
    0.06
    Act Density 0.005%

    No Known Activations