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

    Neuronpedia

    INDEX
    Explanations

    Text passages or quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (<
    -0.08
    Scroll
    -0.07
     Worst
    -0.07
     scholars
    -0.07
     Role
    -0.06
     SON
    -0.06
    Senior
    -0.06
     distributions
    -0.06
    Apply
    -0.06
    -outs
    -0.06
    POSITIVE LOGITS
     interrupted
    0.08
    лаб
    0.07
    INPUT
    0.06
    潜
    0.06
    ایی
    0.06
    ii
    0.06
    유
    0.06
     halted
    0.06
    pling
    0.06
    nav
    0.06
    Act Density 0.066%

    No Known Activations