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

    Neuronpedia

    INDEX
    Explanations

    .com or nutrition websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৷
    0.61
     vice
    0.61
    party
    0.60
    oby
    0.58
     نیٹ
    0.58
    best
    0.56
    addressed
    0.56
    chio
    0.55
    okay
    0.55
    address
    0.55
    POSITIVE LOGITS
     unint
    0.79
     丸
    0.76
     않습니다
    0.74
    㯎
    0.74
    墳
    0.73
     Learned
    0.72
     ముందుకు
    0.72
     polyphen
    0.72
     encountered
    0.71
     செயல்ப
    0.70
    Act Density 0.035%

    No Known Activations