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

    Neuronpedia

    INDEX
    Explanations

    bulk/ulk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intimidated
    -0.07
     mạch
    -0.07
     nosso
    -0.06
     дос
    -0.06
    rides
    -0.06
     halinde
    -0.06
    děl
    -0.06
    ipe
    -0.06
    Listeners
    -0.06
    ington
    -0.06
    POSITIVE LOGITS
     bulk
    0.09
    -redux
    0.07
     athletics
    0.07
    :pk
    0.07
     BL
    0.07
     Bucc
    0.07
     ⇒
    0.07
     '''↵↵
    0.07
     wealthy
    0.07
     """
    0.07
    Act Density 0.005%

    No Known Activations