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

    Neuronpedia

    INDEX
    Explanations

    person to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    会被
    0.53
     được
    0.49
    被
    0.49
     đươ
    0.48
    被人
    0.47
     correction
    0.46
     يكون
    0.46
    ถูก
    0.46
    被打
    0.46
     être
    0.46
    POSITIVE LOGITS
     aware
    0.71
     excited
    0.57
     acquainted
    0.55
     incapable
    0.54
     addicted
    0.48
    interested
    0.48
     alarmed
    0.47
     सहमत
    0.46
     versed
    0.46
    excited
    0.46
    Act Density 0.006%

    No Known Activations