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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ención
    -0.07
    ypsum
    -0.07
     reserva
    -0.07
    .nano
    -0.06
     Prevention
    -0.06
     граждан
    -0.06
    もの
    -0.06
    فران
    -0.06
     momentos
    -0.06
     хотел
    -0.06
    POSITIVE LOGITS
    <>↵
    0.07
    engage
    0.07
     touch
    0.07
     Am
    0.07
     conclude
    0.06
    Organ
    0.06
    '.
    0.06
     remainder
    0.06
    Compiled
    0.06
     refers
    0.06
    Act Density 0.013%

    No Known Activations