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

    Neuronpedia

    INDEX
    Explanations

    Sainthood/canonization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Corrections
    -0.07
     собы
    -0.06
    &
    -0.06
    fé
    -0.06
    िख
    -0.06
     resisted
    -0.06
     landmark
    -0.06
    페
    -0.06
    وسف
    -0.06
     reminder
    -0.06
    POSITIVE LOGITS
    mom
    0.07
    -goal
    0.07
     equalTo
    0.07
    __;
    0.07
    .mvc
    0.07
    �
    0.07
     Jackets
    0.06
    	ext
    0.06
    atomic
    0.06
    ATEGY
    0.06
    Act Density 0.005%

    No Known Activations