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

    Neuronpedia

    INDEX
    Explanations

    Now followed by questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     กี่
    0.46
     অবস্থার
    0.46
    行く
    0.46
     malicious
    0.45
     ቤት
    0.43
     ਤੇ
    0.43
     JSONObject
    0.42
     น้ํา
    0.42
     sustain
    0.42
     lepiej
    0.41
    POSITIVE LOGITS
    Compar
    0.46
    Meta
    0.45
    焖
    0.45
    是对
    0.45
    şt
    0.45
    President
    0.45
    笔者
    0.44
    Correspond
    0.43
    Tienes
    0.43
    Graf
    0.43
    Act Density 0.008%

    No Known Activations