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

    Neuronpedia

    INDEX
    Explanations

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dux
    -0.07
     SIZE
    -0.07
    .xmlbeans
    -0.07
    ií
    -0.07
    leader
    -0.07
    axios
    -0.07
     sentir
    -0.06
    hospital
    -0.06
    諾
    -0.06
     Particle
    -0.06
    POSITIVE LOGITS
     spraw
    0.06
    auto
    0.06
     Ссылки
    0.06
     disgust
    0.06
     hw
    0.06
    �자
    0.06
    .ua
    0.06
     ув
    0.06
    :.
    0.06
     で
    0.06
    Act Density 0.013%

    No Known Activations