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

    Neuronpedia

    INDEX
    Explanations

    jokes and punchlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sexy
    0.48
     hashes
    0.46
     policías
    0.44
     పోలీ
    0.43
     പോലീസ്
    0.43
     uneas
    0.43
     Persever
    0.42
     BUREAU
    0.42
     propietario
    0.41
     alterações
    0.41
    POSITIVE LOGITS
    Roboto
    0.42
    stimulated
    0.40
     مصنوعی
    0.40
    rat
    0.39
    ttä
    0.39
    বিষ
    0.39
    stimulating
    0.38
    Rat
    0.38
     figuring
    0.37
    别
    0.37
    Act Density 0.001%

    No Known Activations