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

    Neuronpedia

    INDEX
    Explanations

    Disk partitioning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     video
    -0.07
    енности
    -0.07
    تز
    -0.06
    Speech
    -0.06
     Domain
    -0.06
     Body
    -0.06
    .Domain
    -0.06
    فت
    -0.06
     calendar
    -0.06
    Batch
    -0.06
    POSITIVE LOGITS
     neo
    0.08
    ฝ
    0.06
    \">"
    0.06
    than
    0.06
    pet
    0.06
     đòi
    0.06
    ,sum
    0.06
    sites
    0.06
     pounds
    0.06
    -wsj
    0.06
    Act Density 0.031%

    No Known Activations