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

    Neuronpedia

    INDEX
    Explanations

    pet personality and care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    staticmethod
    0.42
    羧
    0.39
     твор
    0.39
     achromatic
    0.38
     subparagraph
    0.38
     творчества
    0.37
    wikipedia
    0.36
     simplic
    0.36
     প্রবৃত্ত
    0.36
     उपराष्ट्रपति
    0.36
    POSITIVE LOGITS
     foster
    0.64
     fosters
    0.59
     personality
    0.59
    Personality
    0.59
     personalities
    0.58
     Personality
    0.57
     cudd
    0.57
     FIV
    0.56
     sweetest
    0.55
     fostered
    0.54
    Act Density 0.021%

    No Known Activations