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

    Neuronpedia

    INDEX
    Explanations

    ranking systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     can't
    -0.08
    can't
    -0.08
     accidentally
    -0.08
    impl
    -0.08
    712
    -0.08
     customer's
    -0.07
     unint
    -0.07
     diagrams
    -0.07
    اط
    -0.07
     couldn't
    -0.07
    POSITIVE LOGITS
     shortlist
    0.11
     survived
    0.09
    排名
    0.09
     graduating
    0.09
     qualification
    0.09
    Qualification
    0.09
    資格
    0.09
    晋
    0.09
     survivors
    0.09
     winners
    0.09
    Act Density 0.012%

    No Known Activations