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

    Neuronpedia

    INDEX
    Explanations

    also, addition, moreover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wars
    0.36
    おく
    0.35
    
    0.34
     autopsy
    0.34
     przestr
    0.34
    Damn
    0.34
     でしょう
    0.34
     ही
    0.33
    ENSATION
    0.33
     enormes
    0.33
    POSITIVE LOGITS
    に加え
    0.52
    不但
    0.45
     nejen
    0.44
    だけでなく
    0.38
     በተጨማሪ
    0.38
    不仅
    0.38
     علاوه
    0.37
    酛
    0.36
     selain
    0.36
    ienza
    0.35
    Act Density 0.174%

    No Known Activations