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

    Neuronpedia

    INDEX
    Explanations

    first/boolean logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    073
    -0.07
    lerinde
    -0.07
    209
    -0.06
     شوند
    -0.06
    _PRED
    -0.06
    veh
    -0.06
     позволяет
    -0.06
    ежать
    -0.06
    058
    -0.06
    ्थ
    -0.06
    POSITIVE LOGITS
    _fk
    0.07
    "},
↵
    0.07
    hasil
    0.07
     disag
    0.07
    navbarDropdown
    0.07
    ={['
    0.07
    _PRODUCTS
    0.06
     accordion
    0.06
     k�
    0.06
    ={{↵
    0.06
    Act Density 0.017%

    No Known Activations