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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conduc
    -0.06
     alış
    -0.06
    988
    -0.06
     براى
    -0.06
     weil
    -0.06
     sanctioned
    -0.06
    方案
    -0.06
     základní
    -0.06
     Markets
    -0.06
    strcmp
    -0.06
    POSITIVE LOGITS
     magician
    0.07
    .collect
    0.07
    ognition
    0.06
    .capture
    0.06
     Notify
    0.06
     kurul
    0.06
    <td
    0.06
     Map
    0.06
    umably
    0.06
     spit
    0.06
    Act Density 0.102%

    No Known Activations