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

    Neuronpedia

    INDEX
    Explanations

    Kinship/relatedness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ены
    -0.08
    िना
    -0.08
    inske
    -0.08
     fabric
    -0.08
    ariamente
    -0.07
     attempts
    -0.07
     Analog
    -0.07
    ાઈન
    -0.07
    ائص
    -0.07
    іна
    -0.07
    POSITIVE LOGITS
     altru
    0.10
    援
    0.07
     поруч
    0.07
     выступ
    0.07
     гуман
    0.07
     называют
    0.07
    孔
    0.07
     накоп
    0.07
     trick
    0.07
    _BATCH
    0.07
    Act Density 0.002%

    No Known Activations