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

    Neuronpedia

    INDEX
    Explanations

    describing scenarios or specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㸳
    0.43
     salary
    0.40
    第一时间
    0.40
    atee
    0.39
     параметра
    0.37
    音频
    0.37
    聡
    0.37
     устанавли
    0.36
    פס
    0.36
    嫄
    0.36
    POSITIVE LOGITS
    𝙰
    0.44
    oliko
    0.43
     overwhelmed
    0.41
     zhu
    0.40
    ActivityCompat
    0.40
    ਸ਼ਨ
    0.39
     outbursts
    0.39
     Ed
    0.39
     Edo
    0.39
     Ke
    0.39
    Act Density 0.056%

    No Known Activations