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

    Neuronpedia

    INDEX
    Explanations

    algorithms and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _strike
    -0.07
    (widget
    -0.07
     Miracle
    -0.07
     adults
    -0.06
     Retirement
    -0.06
    _Cell
    -0.06
    (entry
    -0.06
     Apartment
    -0.06
    records
    -0.06
    47
    -0.06
    POSITIVE LOGITS
    )*
    0.08
     Acting
    0.06
     peux
    0.06
     tiger
    0.06
     Gör
    0.06
    .;
    0.06
     сбор
    0.06
    ज़
    0.06
    *dx
    0.06
    임
    0.06
    Act Density 0.021%

    No Known Activations