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

    Neuronpedia

    INDEX
    Explanations

    code and data formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chaired
    0.79
     unab
    0.78
     सका
    0.77
    щиков
    0.75
     unim
    0.74
     Над
    0.74
     kteří
    0.73
     indist
    0.73
    щика
    0.72
    ieurs
    0.72
    POSITIVE LOGITS
    ####
    1.03
    <blockquote>
    1.02
    ed
    1.01
    ের
    1.00
    if
    0.98
     xī
    0.98
    aop
    0.98
     memang
    0.94
    वारी
    0.93
    ###
    0.91
    Act Density 0.674%

    No Known Activations