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

    Neuronpedia

    INDEX
    Explanations

    sequential parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בישראל
    -0.07
    쮸
    -0.07
    H
    -0.07
     Addiction
    -0.07
    нако
    -0.07
    di
    -0.07
    油脂
    -0.07
    Southern
    -0.07
    Bush
    -0.06
     plants
    -0.06
    POSITIVE LOGITS
     azt
    0.08
    (speed
    0.08
    _boundary
    0.07
    >Hello
    0.07
     Cmd
    0.07
    뮘
    0.07
    :not
    0.06
     narrowing
    0.06
     ange
    0.06
    减排
    0.06
    Act Density 0.005%

    No Known Activations