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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    担当
    -0.06
    uploaded
    -0.06
    .fastjson
    -0.06
    sci
    -0.06
    سي
    -0.06
    approx
    -0.06
     FormData
    -0.06
     Κο
    -0.06
     Charlottesville
    -0.06
    "}↵↵
    -0.06
    POSITIVE LOGITS
     rostlin
    0.07
    aptop
    0.07
     Rift
    0.06
    elyn
    0.06
     queued
    0.06
     رسول
    0.06
    |:
    0.06
    اءة
    0.06
     Rail
    0.06
    151
    0.06
    Act Density 0.009%

    No Known Activations