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

    Neuronpedia

    INDEX
    Explanations

    often brief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     согласо
    0.49
    คาเดมี
    0.48
     สํา
    0.47
    ෙන්ම
    0.47
    </h3>
    0.46
    藪
    0.46
     surjective
    0.46
     adjacency
    0.45
    不用
    0.45
     congratulated
    0.45
    POSITIVE LOGITS
    Taste
    0.53
    Photo
    0.48
    ======
    0.45
    া
    0.45
    Opp
    0.44
    জ
    0.44
    Tata
    0.43
    ান্ট
    0.43
    Alien
    0.42
    errorHandler
    0.42
    Act Density 0.000%

    No Known Activations