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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceramic
    -0.07
    odář
    -0.06
    _node
    -0.06
    者の
    -0.06
     reconstruct
    -0.06
    ้าค
    -0.06
    -sale
    -0.06
     crushers
    -0.06
     genital
    -0.06
     payroll
    -0.06
    POSITIVE LOGITS
    emphasis
    0.07
    phoon
    0.07
    subscriber
    0.07
     pointer
    0.07
     IEnumerator
    0.07
     Roberto
    0.07
    umo
    0.06
     француз
    0.06
    Tower
    0.06
     投稿日
    0.06
    Act Density 0.003%

    No Known Activations