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

    Neuronpedia

    INDEX
    Explanations

    global development and policy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    імеч
    -0.08
     نگهداری
    -0.07
    exceptions
    -0.07
     careg
    -0.07
    ُوا
    -0.06
     руч
    -0.06
    оди
    -0.06
    имости
    -0.06
    "context
    -0.06
    (si
    -0.06
    POSITIVE LOGITS
    338
    0.06
     signify
    0.06
    %/
    0.06
     SHIPPING
    0.06
    olulu
    0.06
    бора
    0.06
    .Alpha
    0.06
     precarious
    0.05
    개발
    0.05
     endwhile
    0.05
    Act Density 0.048%

    No Known Activations