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

    Neuronpedia

    INDEX
    Explanations

    social media following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x93>
    0.51
    他人
    0.49
    每次
    0.48
     కనిప
    0.48
    <0x9D>
    0.48
    孩子
    0.47
     použ
    0.46
     حكم
    0.46
    ين
    0.46
    支付
    0.45
    POSITIVE LOGITS
     Twitter
    0.65
     Follow
    0.62
    Follow
    0.58
    </h1>
    0.55
    </b>
    0.55
     फॉलो
    0.54
    </h3>
    0.52
     twitter
    0.52
     FOLLOW
    0.52
     followup
    0.51
    Act Density 0.004%

    No Known Activations