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

    Neuronpedia

    INDEX
    Explanations

    male preference in job descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dose
    0.49
    +)
    0.43
    ähne
    0.42
    astro
    0.40
    ਨ੍ਹਾਂ
    0.39
    +{
    0.39
     astro
    0.38
    +|
    0.38
    delta
    0.38
    terms
    0.37
    POSITIVE LOGITS
    နည်း
    0.40
     রংপুর
    0.39
    崠
    0.39
     ngu
    0.39
     puno
    0.39
     benefici
    0.39
    嬂
    0.38
    酝
    0.38
     Sakurai
    0.38
    類型
    0.38
    Act Density 0.001%

    No Known Activations