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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conway
    -0.06
    平方
    -0.06
    кой
    -0.06
     Yeni
    -0.06
    mium
    -0.06
     jp
    -0.06
    ):(
    -0.06
    $name
    -0.06
     деньги
    -0.06
     involuntary
    -0.06
    POSITIVE LOGITS
     recordings
    0.08
    AL
    0.06
     paired
    0.06
     testimonials
    0.06
    beeld
    0.06
     nameLabel
    0.06
    ีการ
    0.06
     iets
    0.06
     GAL
    0.06
    icens
    0.06
    Act Density 0.007%

    No Known Activations