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

    Neuronpedia

    INDEX
    Explanations

    Okay, I understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     malu
    0.85
    ^^
    0.84
    縦
    0.79
     mese
    0.78
     ^^
    0.74
    Stub
    0.73
    温泉
    0.73
     merry
    0.73
    ιών
    0.71
     cuddling
    0.71
    POSITIVE LOGITS
     understood
    0.69
    되었습니다
    0.65
     Katherine
    0.65
    душ
    0.65
     Etat
    0.63
    攏
    0.63
     परिवर्तित
    0.62
     understands
    0.61
     valid
    0.60
     выполня
    0.60
    Act Density 0.090%

    No Known Activations