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

    Neuronpedia

    INDEX
    Explanations

    translation and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    É
    0.50
    Про
    0.49
    Д
    0.49
    На
    0.46
    Т
    0.46
      
    0.44
    Ско
    0.43
    תו
    0.43
    Се
    0.42
    Avec
    0.42
    POSITIVE LOGITS
     позднее
    0.51
     സ്വാതന്ത്ര
    0.50
     சுதந்திர
    0.50
    skirts
    0.49
     ብዙውን
    0.47
     nebude
    0.47
    шов
    0.46
    ag
    0.46
     entidad
    0.46
    ov
    0.46
    Act Density 0.001%

    No Known Activations