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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    odied
    -0.07
    XD
    -0.07
    lace
    -0.06
     Also
    -0.06
     Patriot
    -0.06
     تبلی
    -0.06
     هن
    -0.06
     çarp
    -0.06
    нак
    -0.06
     applicants
    -0.06
    POSITIVE LOGITS
     name
    0.07
    'name
    0.07
    name
    0.07
    Susan
    0.06
    substr
    0.06
     hydro
    0.06
    displayName
    0.06
     dispersed
    0.06
    abil
    0.06
    ARRY
    0.06
    Act Density 0.001%

    No Known Activations