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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -к
    -0.07
     pomáh
    -0.06
    ूं
    -0.06
     ""↵↵
    -0.06
    VE
    -0.06
     двух
    -0.06
     scarce
    -0.06
     CSP
    -0.06
    .textContent
    -0.06
     رسمی
    -0.06
    POSITIVE LOGITS
    WARD
    0.07
     guidelines
    0.07
     upgrade
    0.07
     habitats
    0.07
     register
    0.06
     load
    0.06
    etler
    0.06
    станов
    0.06
    czy
    0.06
     useRouter
    0.06
    Act Density 0.637%

    No Known Activations