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

    Neuronpedia

    INDEX
    Explanations

    US Navy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     employing
    -0.06
     khác
    -0.06
    ，与
    -0.06
     non
    -0.06
     safe
    -0.06
     halde
    -0.06
    bestos
    -0.06
     age
    -0.06
     CENTER
    -0.06
    ิหาร
    -0.06
    POSITIVE LOGITS
    conversion
    0.07
    weis
    0.07
     parce
    0.07
    欧
    0.06
     berries
    0.06
    _attribute
    0.06
     zby
    0.06
     MLP
    0.06
    element
    0.06
    INED
    0.06
    Act Density 0.038%

    No Known Activations