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

    Neuronpedia

    INDEX
    Explanations

    performance gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endTime
    -0.07
    remark
    -0.06
    ((((
    -0.06
    間
    -0.06
     cellForRowAt
    -0.06
    GLOSS
    -0.06
     Hash
    -0.05
    .members
    -0.05
    locked
    -0.05
    .valid
    -0.05
    POSITIVE LOGITS
    -covered
    0.07
     submarines
    0.07
    abal
    0.07
     skating
    0.07
     accumulating
    0.07
    aphael
    0.07
     hamstring
    0.07
     subdued
    0.07
    ensburg
    0.06
    _sync
    0.06
    Act Density 0.018%

    No Known Activations