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

    Neuronpedia

    INDEX
    Explanations

    characteristic to quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কাব
    0.41
     பிர
    0.39
    寒
    0.39
    破坏
    0.39
     '-',
    0.37
     കൊല്ല
    0.36
    шень
    0.36
    핀
    0.36
    ième
    0.35
     Еўро
    0.35
    POSITIVE LOGITS
    ̂
    0.41
     Missionary
    0.38
     beloved
    0.38
     Jn
    0.38
     undivided
    0.37
    则是
    0.37
     urge
    0.36
     way
    0.36
     empt
    0.36
     Treatment
    0.36
    Act Density 0.000%

    No Known Activations