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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truths
    -0.07
     grace
    -0.07
     ohne
    -0.07
    sequences
    -0.07
     deserve
    -0.07
     firsthand
    -0.07
    ducers
    -0.07
    (cal
    -0.07
     shape
    -0.07
    là
    -0.07
    POSITIVE LOGITS
     broadcast
    0.08
     nội
    0.08
    烛
    0.07
    Furthermore
    0.07
    .elementAt
    0.07
    boa
    0.07
    亲友
    0.07
     pParent
    0.07
    _VF
    0.07
    까지
    0.07
    Act Density 0.002%

    No Known Activations