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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Конгре
    0.43
    ularity
    0.43
    ꔰ
    0.40
    гө
    0.40
     uitge
    0.39
     tiêu
    0.38
    电信
    0.38
    乑
    0.38
     uç
    0.38
     ওয়াল
    0.38
    POSITIVE LOGITS
     eyes
    0.51
    ness
    0.50
    NESS
    0.49
    EST
    0.49
     manner
    0.46
    est
    0.45
    ly
    0.44
     reflection
    0.44
     quiet
    0.44
      
    0.43
    Act Density 0.000%

    No Known Activations