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

    Neuronpedia

    INDEX
    Explanations

    Organization name changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posix
    -0.07
     abused
    -0.07
     prim
    -0.07
    ौड
    -0.06
     stamina
    -0.06
    best
    -0.06
     클래스
    -0.06
    .DTO
    -0.06
    .ob
    -0.06
     ''
    -0.06
    POSITIVE LOGITS
    HashMap
    0.06
    کل
    0.06
     господар
    0.06
    .feedback
    0.06
    DEN
    0.06
     oluşan
    0.06
    цин
    0.06
    执
    0.06
    FLOAT
    0.06
    :eq
    0.06
    Act Density 0.059%

    No Known Activations