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
    Levels
    -0.07
    때
    -0.07
     wereld
    -0.06
    -ext
    -0.06
    Owned
    -0.06
     snacks
    -0.06
     прор
    -0.06
    atched
    -0.06
    RR
    -0.06
     GSL
    -0.06
    POSITIVE LOGITS
    /calendar
    0.07
    فس
    0.07
    azy
    0.06
    fell
    0.06
     traitement
    0.06
     onUpdate
    0.06
    'image
    0.06
    онів
    0.06
     incess
    0.06
     marketing
    0.06
    Act Density 0.011%

    No Known Activations