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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Relevant
    -0.06
    全球
    -0.06
     although
    -0.06
    Chance
    -0.06
    JI
    -0.06
    -g
    -0.06
     intim
    -0.06
    ansa
    -0.06
     Amazing
    -0.06
     RESPONS
    -0.06
    POSITIVE LOGITS
     خصوص
    0.08
     mapped
    0.07
    /bash
    0.07
     même
    0.07
     	↵
    0.07
     روح
    0.06
    ψη
    0.06
     fict
    0.06
     recommended
    0.06
     listens
    0.06
    Act Density 0.018%

    No Known Activations