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

    Neuronpedia

    INDEX
    Explanations

    ellipsis, punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viagem
    0.27
    CM
    0.27
     mobilize
    0.26
    RCT
    0.26
    CMS
    0.26
    CE
    0.25
    Data
    0.25
    Quin
    0.25
    ிகளும்
    0.25
    cheduled
    0.24
    POSITIVE LOGITS
    孬
    0.29
    </h3>
    0.28
     という
    0.27
     إنه
    0.27
     فقد
    0.26
     jeweiligen
    0.26
     Elke
    0.26
     そして
    0.26
     چاہیے۔
    0.25
    袄
    0.25
    Act Density 0.000%

    No Known Activations