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

    Neuronpedia

    INDEX
    Explanations

    Underscores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فرز
    -0.06
     },↵↵
    -0.06
     bully
    -0.06
    coe
    -0.06
    837
    -0.06
    875
    -0.06
     oma
    -0.06
    	fail
    -0.06
    ???↵↵
    -0.06
    .ForEach
    -0.06
    POSITIVE LOGITS
     conducting
    0.07
     talent
    0.07
    Leading
    0.07
     inhab
    0.07
     sophisticated
    0.07
    ining
    0.07
     sept
    0.06
     palabra
    0.06
     میزان
    0.06
     plugins
    0.06
    Act Density 0.039%

    No Known Activations