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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cohorts
    -0.07
     trh
    -0.06
     Players
    -0.06
     securities
    -0.06
    .accessToken
    -0.06
    mayı
    -0.06
    IllegalAccessException
    -0.06
    >();↵↵
    -0.06
     takeaway
    -0.06
     membr
    -0.05
    POSITIVE LOGITS
     lúc
    0.07
    .apiUrl
    0.07
     financed
    0.07
    equiv
    0.07
    trag
    0.07
     purely
    0.07
     occupy
    0.07
     هنگام
    0.06
     turned
    0.06
    !!!!!
    0.06
    Act Density 0.121%

    No Known Activations