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

    Neuronpedia

    INDEX
    Explanations

    code setup commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    학년
    0.39
    awanda
    0.38
     다음
    0.38
     마을
    0.37
    謄
    0.36
    交流
    0.36
     போது
    0.36
    Streak
    0.36
    走到
    0.36
     وهم
    0.35
    POSITIVE LOGITS
     submarines
    0.43
    மாத
    0.40
     Guides
    0.39
     rayos
    0.39
     bilgi
    0.38
    publishing
    0.38
    رین
    0.37
     journalism
    0.37
     quark
    0.37
    ̦
    0.37
    Act Density 0.004%

    No Known Activations