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

    Neuronpedia

    INDEX
    Explanations

    tailor to customize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dazu
    0.93
     Allerdings
    0.88
     Ako
    0.78
     Discussion
    0.77
     Debian
    0.77
     Frage
    0.75
     Daar
    0.75
     Où
    0.75
     Hadoop
    0.74
     Frankly
    0.74
    POSITIVE LOGITS
     during
    0.89
     recientemente
    0.88
     lately
    0.85
     ఇటీవల
    0.74
     சமீப
    0.73
     récentes
    0.73
    弹性
    0.73
     বেড়েছে
    0.72
     bosque
    0.71
     disminución
    0.71
    Act Density 0.082%

    No Known Activations