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

    Neuronpedia

    INDEX
    Explanations

    chatbots and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एमसीक्यू
    0.50
    丳
    0.50
    帙
    0.48
    آ
    0.47
    簹
    0.46
    篂
    0.46
     الضرب
    0.45
    ों
    0.44
    ෙන්ම
    0.44
    ებლ
    0.43
    POSITIVE LOGITS
     bonuses
    0.55
     mascot
    0.52
     services
    0.51
     supports
    0.51
     service
    0.50
     persona
    0.48
     bonus
    0.47
     masc
    0.47
     pace
    0.46
     saloon
    0.45
    Act Density 0.009%

    No Known Activations