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

    Neuronpedia

    INDEX
    Explanations

    intensifier followed by complexity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iox
    0.75
     wealthier
    0.73
     thoughtful
    0.70
     interesting
    0.68
     excess
    0.67
    reb
    0.67
    äk
    0.67
    َال
    0.66
     luxurious
    0.66
    imals
    0.66
    POSITIVE LOGITS
     culprits
    0.78
     গন্ধ
    0.74
     culprit
    0.68
     ಅರ್ಜಿ
    0.65
    ርድ
    0.65
    อนไลน์
    0.64
    Error
    0.63
    술
    0.62
     thủ
    0.62
    器件
    0.62
    Act Density 0.239%

    No Known Activations