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

    Neuronpedia

    INDEX
    Explanations

    Area measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المالية
    -0.07
     לל
    -0.07
     Dash
    -0.07
     dance
    -0.07
     complained
    -0.07
     watch
    -0.07
     laughed
    -0.07
    一笑
    -0.06
    蟾
    -0.06
     לעמוד
    -0.06
    POSITIVE LOGITS
     spectro
    0.08
    ├
    0.08
    0.08
     Portug
    0.08
    Didn
    0.07
    estruction
    0.07
    TEGR
    0.07
    ourg
    0.07
    💬
    0.07
     recommend
    0.07
    Act Density 0.001%

    No Known Activations