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

    Neuronpedia

    INDEX
    Explanations

    horror story

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ĝ
    0.50
     меку
    0.47
    лаго
    0.47
     Sql
    0.47
     dinast
    0.47
     За
    0.46
     راز
    0.46
     ciencias
    0.46
     Ото
    0.44
    وی
    0.44
    POSITIVE LOGITS
    తలు
    0.44
    )。
    0.43
    chende
    0.43
    ørende
    0.42
    尽可能
    0.41
    的基础
    0.41
    한
    0.41
    ្នុង
    0.41
    分别是
    0.41
    eburger
    0.41
    Act Density 0.001%

    No Known Activations