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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Printf
    -0.07
     isa
    -0.07
     AFC
    -0.07
     ترجم
    -0.06
    小姐
    -0.06
    BAL
    -0.06
    -enter
    -0.06
     акти
    -0.06
     власти
    -0.06
     сло
    -0.06
    POSITIVE LOGITS
    ��
    0.09
    }↵
    0.07
     Alumni
    0.06
    Available
    0.06
    	success
    0.06
    }↵↵↵↵↵↵
    0.06
    Customers
    0.06
    <img
    0.06
    COMPARE
    0.06
    جة
    0.06
    Act Density 0.000%

    No Known Activations