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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᵧ
    -0.07
    _migration
    -0.07
    לחץ
    -0.07
    .oracle
    -0.07
     iota
    -0.07
    oley
    -0.07
    _taxonomy
    -0.07
    Writable
    -0.07
     العالي
    -0.06
    setParameter
    -0.06
    POSITIVE LOGITS
     Ni
    0.07
     […
    0.07
     BED
    0.07
     дост
    0.07
    (api
    0.07
    .Result
    0.06
    ')]↵
    0.06
     Berlin
    0.06
     ADD
    0.06
    类型的
    0.06
    Act Density 0.013%

    No Known Activations