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

    Neuronpedia

    INDEX
    Explanations

    speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .popup
    -0.07
    Driven
    -0.06
     досить
    -0.06
    -LAST
    -0.06
     UserDefaults
    -0.06
    GRID
    -0.06
     Claims
    -0.06
     sandwich
    -0.06
     часом
    -0.06
    DEM
    -0.06
    POSITIVE LOGITS
    аніз
    0.07
    orgetown
    0.07
    sher
    0.06
    ffer
    0.06
    ---------↵
    0.06
    tgt
    0.06
    fer
    0.06
    Che
    0.06
    liš
    0.06
    MYSQL
    0.06
    Act Density 0.044%

    No Known Activations