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

    Neuronpedia

    INDEX
    Explanations

    more than, not just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ted
    -0.08
    pile
    -0.08
     versa
    -0.08
    纬
    -0.08
    ucin
    -0.08
    spann
    -0.07
     oraz
    -0.07
     tollen
    -0.07
    /general
    -0.07
    ürd
    -0.07
    POSITIVE LOGITS
     cornerstone
    0.09
     contractual
    0.08
     fleeting
    0.08
     belonging
    0.07
     انتقال
    0.07
     ponte
    0.07
     melod
    0.07
     intellectual
    0.07
     translators
    0.07
     Shepherd
    0.07
    Act Density 0.011%

    No Known Activations