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

    Neuronpedia

    INDEX
    Explanations

    health or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ക്ക്‌
    0.82
    อา
    0.76
    㚐
    0.72
     حکم
    0.71
    폰
    0.70
    russian
    0.69
     сообщение
    0.69
     Cocker
    0.67
     عن
    0.67
    locate
    0.67
    POSITIVE LOGITS
     lifestyle
    0.75
    chainId
    0.72
     líqu
    0.72
     diaries
    0.70
    捻
    0.69
     느
    0.67
    uchsia
    0.67
     twisted
    0.67
     additives
    0.66
     hormones
    0.66
    Act Density 0.008%

    No Known Activations