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

    Neuronpedia

    INDEX
    Explanations

    Evan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SAMPLE
    -0.07
     هفته
    -0.06
     Lawyers
    -0.06
    Inspector
    -0.06
     rhythms
    -0.06
    .enabled
    -0.06
    homes
    -0.06
     oli
    -0.06
     عليها
    -0.06
    (express
    -0.06
    POSITIVE LOGITS
    -even
    0.06
    uthor
    0.06
    .detach
    0.06
    ับร
    0.06
    мотря
    0.05
    。</
    0.05
    [])↵
    0.05
     Drive
    0.05
    �
    0.05
    mán
    0.05
    Act Density 0.160%

    No Known Activations