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

    Neuronpedia

    INDEX
    Explanations

    protect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amentos
    -0.07
    uentes
    -0.07
    ої
    -0.06
     recreation
    -0.06
    мента
    -0.06
    _payment
    -0.06
    'clock
    -0.06
    'être
    -0.06
    Ế
    -0.06
    rex
    -0.06
    POSITIVE LOGITS
     protect
    0.07
     Protection
    0.07
     Ptr
    0.06
     Symposium
    0.06
     defending
    0.06
    !:
    0.06
    .children
    0.06
     protects
    0.06
     Tit
    0.06
     protecting
    0.06
    Act Density 0.038%

    No Known Activations