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

    Neuronpedia

    INDEX
    Explanations

    goes against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     went
    0.55
     gone
    0.54
     gått
    0.51
     gikk
    0.46
    went
    0.45
     gick
    0.45
    ไป
    0.45
     gaan
    0.45
     Going
    0.43
     goin
    0.43
    POSITIVE LOGITS
     objectForKey
    0.39
     육
    0.38
    Hash
    0.37
    简单的
    0.37
     जुड़ा
    0.36
    MyAdmin
    0.36
     사용하여
    0.36
    𝘔
    0.36
    数
    0.36
     рис
    0.35
    Act Density 0.007%

    No Known Activations