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

    Neuronpedia

    INDEX
    Explanations

    Technical and news topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eleven
    -0.07
     closely
    -0.07
     wherever
    -0.07
    ital
    -0.06
     disparities
    -0.06
     remarkable
    -0.06
     african
    -0.06
     해
    -0.06
     Popular
    -0.06
    frog
    -0.06
    POSITIVE LOGITS
     Ges
    0.07
    -cart
    0.06
    िरफ
    0.06
    /message
    0.06
    -derived
    0.06
     k
    0.06
    /St
    0.06
    ‌ک
    0.06
     پس
    0.06
    .sb
    0.06
    Act Density 0.064%

    No Known Activations