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

    Neuronpedia

    INDEX
    Explanations

    accidents and injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    顯
    -0.07
    _Path
    -0.06
     вывод
    -0.06
     Validation
    -0.06
    変
    -0.06
    -model
    -0.06
     Apprec
    -0.06
    Gap
    -0.06
    mom
    -0.06
    щие
    -0.06
    POSITIVE LOGITS
    INavigation
    0.08
     bach
    0.07
     soup
    0.07
    .kafka
    0.07
    .observable
    0.07
    .”↵↵↵↵
    0.06
    amespace
    0.06
     awaiting
    0.06
    ulur
    0.06
    (slug
    0.06
    Act Density 0.063%

    No Known Activations