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

    Neuronpedia

    INDEX
    Explanations

    work followed by verbs/prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    った
    2.55
    ce
    2.44
    ında
    2.20
    на
    2.09
    ان
    2.06
    qu
    1.91
    时候
    1.87
    vär
    1.84
    す
    1.84
    जनक
    1.83
    POSITIVE LOGITS
    াকিস্ত
    2.16
     havoc
    2.09
    CES
    2.05
    Kết
    2.02
    CAR
    1.96
     dispel
    1.93
    𝘾
    1.89
     inlay
    1.84
     intend
    1.82
     étroite
    1.80
    Act Density 0.154%

    No Known Activations