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

    Neuronpedia

    INDEX
    Explanations

    parenthesis and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，就
    -0.07
    ounced
    -0.06
    Recipe
    -0.06
    LoggedIn
    -0.06
     люб
    -0.06
    ouples
    -0.06
    _loc
    -0.06
     O
    -0.06
    _CHO
    -0.06
     유형
    -0.06
    POSITIVE LOGITS
    ']=
    0.07
    )$/
    0.06
    chai
    0.06
     deleting
    0.06
    temp
    0.06
    activate
    0.06
     Cald
    0.06
     arises
    0.06
     yaptığ
    0.06
     Physicians
    0.06
    Act Density 0.011%

    No Known Activations