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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аток
    -0.07
     Challenges
    -0.07
    ublik
    -0.07
    (Vector
    -0.07
    _helpers
    -0.06
     Cathedral
    -0.06
     到
    -0.06
     bathrooms
    -0.06
    credential
    -0.06
     accommodation
    -0.06
    POSITIVE LOGITS
    啊啊
    0.08
    adia
    0.06
    isclosed
    0.06
    명의
    0.06
    ousel
    0.06
    ,temp
    0.06
     moreover
    0.06
     às
    0.06
     빠
    0.06
    '}
    0.06
    Act Density 0.973%

    No Known Activations