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

    Neuronpedia

    INDEX
    Explanations

    Best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Subscribe
    -0.07
     broadcasting
    -0.06
    -article
    -0.06
    の大
    -0.06
    -Cola
    -0.06
     foes
    -0.06
     '-
    -0.06
    -found
    -0.06
     Lia
    -0.06
    .inner
    -0.06
    POSITIVE LOGITS
    دیگر
    0.07
    =''
    0.07
     discrepancies
    0.07
    _bh
    0.06
    524
    0.06
     clientId
    0.06
    Cluster
    0.06
    ره
    0.06
    inated
    0.06
     motivate
    0.06
    Act Density 0.084%

    No Known Activations