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

    Neuronpedia

    INDEX
    Explanations

    Smaller-scale organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posX
    -0.07
     startX
    -0.06
     Verd
    -0.06
     minh
    -0.06
     smoking
    -0.06
    liers
    -0.06
     NoSuch
    -0.06
     near
    -0.06
     Ceremony
    -0.06
     sniper
    -0.06
    POSITIVE LOGITS
     filename
    0.07
     **↵
    0.07
    hopefully
    0.06
     Hopefully
    0.06
    ORM
    0.06
     decorator
    0.06
    VE
    0.06
    rparr
    0.06
    ―
    0.06
    �
    0.06
    Act Density 0.097%

    No Known Activations