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

    Neuronpedia

    INDEX
    Explanations

    Source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SHAPE
    -0.08
    òa
    -0.07
    olution
    -0.07
    _SUPPORTED
    -0.07
    �
    -0.06
     Improvement
    -0.06
     deduction
    -0.06
    付出
    -0.06
     Üniversites
    -0.06
     ipt
    -0.06
    POSITIVE LOGITS
    Sampler
    0.07
     weil
    0.06
     lớn
    0.06
    📑
    0.06
    cling
    0.06
    #[
    0.06
    бы
    0.06
    هائي
    0.06
    די
    0.06
    ]");↵
    0.06
    Act Density 0.007%

    No Known Activations