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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    67
    -0.06
    (horizontal
    -0.06
    /ic
    -0.06
     defaultProps
    -0.06
    /ws
    -0.06
    Answers
    -0.06
    ']",
    -0.06
    _k
    -0.06
    '],
↵
    -0.06
    ****/↵
    -0.06
    POSITIVE LOGITS
     recognizes
    0.07
    isan
    0.07
    сты
    0.06
    stice
    0.06
     indefinitely
    0.06
    。その
    0.06
     supern
    0.06
    iff
    0.06
     ethnic
    0.06
     constitutes
    0.06
    Act Density 0.210%

    No Known Activations