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

    Neuronpedia

    INDEX
    Explanations

    ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _added
    -0.07
     fairy
    -0.07
     builders
    -0.07
    .feed
    -0.06
     bj
    -0.06
     kus
    -0.06
    (peer
    -0.06
     plunged
    -0.06
     molecule
    -0.06
     Moroccan
    -0.06
    POSITIVE LOGITS
    )...
    0.06
     Allows
    0.06
    shore
    0.06
    ��
    0.06
    78
    0.06
     commemorate
    0.06
    变化
    0.06
     SAR
    0.06
     setEmail
    0.06
    ，它
    0.06
    Act Density 0.012%

    No Known Activations