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

    Neuronpedia

    INDEX
    Explanations

    Long-form and casual writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disciple
    -0.07
     contradict
    -0.07
     initiative
    -0.06
     budete
    -0.06
     tá
    -0.06
     pá
    -0.06
    mit
    -0.06
     Wilson
    -0.06
     propor
    -0.06
     onData
    -0.06
    POSITIVE LOGITS
    -yyyy
    0.07
    �
    0.06
    海外
    0.06
     Porsche
    0.06
    -low
    0.06
    .numpy
    0.06
    (ne
    0.06
    _percent
    0.06
     Huyện
    0.06
     دي
    0.06
    Act Density 0.052%

    No Known Activations