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

    Neuronpedia

    INDEX
    Explanations

    furniture and rooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    宩
    0.52
     runtime
    0.49
     pursuant
    0.49
     priority
    0.47
     influencing
    0.47
     learnings
    0.46
     فوتب
    0.45
     motivates
    0.45
     goals
    0.44
     gameplay
    0.43
    POSITIVE LOGITS
     стены
    0.51
     wooden
    0.50
    仪器
    0.50
    ジャケット
    0.49
     embroidered
    0.48
    椅子
    0.48
     тол
    0.48
     помещение
    0.47
     деревя
    0.46
    ステンレス
    0.46
    Act Density 0.086%

    No Known Activations