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

    Neuronpedia

    INDEX
    Explanations

    COL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paranormal
    -0.07
     Hum
    -0.06
    ,:),
    -0.06
    =num
    -0.06
    ¥
    -0.06
     chambre
    -0.06
    VM
    -0.06
    -0.06
    /dc
    -0.06
     películ
    -0.06
    POSITIVE LOGITS
     quil
    0.07
    individual
    0.07
     realize
    0.06
    -using
    0.06
    たい
    0.06
     кир
    0.06
    どう
    0.06
    <![
    0.06
    Different
    0.06
     почему
    0.06
    Act Density 0.101%

    No Known Activations