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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("../
    -0.07
    正式
    -0.07
    productId
    -0.07
    vation
    -0.06
     Glen
    -0.06
     меж
    -0.06
     краї
    -0.06
    ́
    -0.06
    ｜
    -0.06
     meaningful
    -0.06
    POSITIVE LOGITS
    _units
    0.07
     thousands
    0.07
     بك
    0.06
    933
    0.06
    kits
    0.06
     wrink
    0.06
    効
    0.06
     scholarships
    0.06
     plaintext
    0.06
    .submit
    0.06
    Act Density 0.004%

    No Known Activations