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

    Neuronpedia

    INDEX
    Explanations

    Defaults to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Init
    0.75
     Opportunities
    0.74
    #/
    0.73
     Opportunity
    0.72
     Blessing
    0.72
    ;<
    0.72
    ^{*}$
    0.71
     Certain
    0.70
    /"><
    0.69
    Certain
    0.69
    POSITIVE LOGITS
     हैं
    0.91
     ਰਹ
    0.84
     है
    0.84
     are
    0.83
     été
    0.81
     avoids
    0.78
    คือ
    0.78
     showcases
    0.78
     saranno
    0.78
     compares
    0.75
    Act Density 0.023%

    No Known Activations