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

    Neuronpedia

    INDEX
    Explanations

    consistently ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arquitectura
    0.54
    艺术家
    0.52
     acteur
    0.48
     Latinoamérica
    0.48
    ナソニック
    0.48
     искусство
    0.47
    嘉宾
    0.46
    艺术
    0.46
     FaceTime
    0.46
    赞
    0.46
    POSITIVE LOGITS
     a
    0.56
    Okay
    0.53
     effectu
    0.48
     mikt
    0.47
    ຈ
    0.47
    t
    0.46
    auft
    0.46
    ts
    0.45
    š
    0.45
     большого
    0.45
    Act Density 0.000%

    No Known Activations