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

    Neuronpedia

    INDEX
    Explanations

    leading and leadership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রতী
    0.71
    ussels
    0.68
     ogranic
    0.67
    魇
    0.67
    querque
    0.66
    ussel
    0.64
     obligatorio
    0.64
    肄
    0.63
    ojis
    0.63
    परी
    0.62
    POSITIVE LOGITS
     lead
    5.02
     leading
    4.81
     leads
    4.80
     Lead
    4.57
    Lead
    4.47
    lead
    4.43
    Leading
    4.42
     Leading
    4.36
     Leads
    4.35
    leading
    4.33
    Act Density 0.559%

    No Known Activations