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

    Neuronpedia

    INDEX
    Explanations

    stability, ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    累
    -0.08
    rement
    -0.08
    累计
    -0.08
    薪
    -0.08
     labels
    -0.08
    levant
    -0.08
    .tags
    -0.07
     customary
    -0.07
    salary
    -0.07
     Ultimately
    -0.07
    POSITIVE LOGITS
    稳定
    0.13
     stability
    0.13
     stabile
    0.13
     Stability
    0.12
     stabilize
    0.12
     안정
    0.12
     stable
    0.11
     стабиль
    0.11
     stabil
    0.11
     estabilidad
    0.11
    Act Density 0.007%

    No Known Activations