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

    Neuronpedia

    INDEX
    Explanations

    leadership skills and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prevalence
    2.75
    в
    2.75
    为此
    2.55
     unmet
    2.46
     seguros
    2.37
     оказа
    2.37
    clearInterval
    2.36
    en
    2.35
    认为
    2.35
     nara
    2.34
    POSITIVE LOGITS
    س
    4.73
    ية
    4.26
    د
    4.08
    น
    3.74
    ం
    3.66
    𝐩
    3.61
    ه
    3.58
    n
    3.58
    𝐞
    3.54
    𝐢
    3.38
    Act Density 0.007%

    No Known Activations