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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    орів
    -0.07
    авлива
    -0.07
    zm
    -0.07
     sixty
    -0.07
    ження
    -0.07
    460
    -0.06
    Bat
    -0.06
     Hearth
    -0.06
    لمة
    -0.06
    Milliseconds
    -0.06
    POSITIVE LOGITS
    -Allow
    0.08
     میک
    0.06
    .FromResult
    0.06
    ">&#
    0.06
    >{$
    0.06
    -gradient
    0.06
    　ヾ
    0.06
     позд
    0.06
    ="//
    0.06
     erot
    0.06
    Act Density 0.034%

    No Known Activations