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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    печ
    -0.06
    sw
    -0.06
    ">',↵
    -0.06
    �
    -0.06
    									↵
    -0.06
    ranking
    -0.06
    .*?)
    -0.06
    ，有
    -0.06
     її
    -0.06
     чес
    -0.06
    POSITIVE LOGITS
     Seed
    0.07
    .constant
    0.07
     constructor
    0.07
     Prism
    0.06
     cannabis
    0.06
    lust
    0.06
     charities
    0.06
    ATRIX
    0.06
     Jou
    0.06
     Proud
    0.06
    Act Density 0.001%

    No Known Activations