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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tu
    -0.07
    ços
    -0.07
     FOLLOW
    -0.07
    xBD
    -0.06
    蛇
    -0.06
    endcode
    -0.06
    samples
    -0.06
    สาห
    -0.06
    ở
    -0.06
     spoiler
    -0.06
    POSITIVE LOGITS
    names
    0.07
     primary
    0.07
     언제
    0.06
    	onChange
    0.06
     onChange
    0.06
     embark
    0.06
    .force
    0.06
     Alberto
    0.06
    维
    0.06
     uyar
    0.06
    Act Density 0.000%

    No Known Activations