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

    Neuronpedia

    INDEX
    Explanations

    membership forms, local restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പൂര്‍
    0.49
    kü
    0.48
    দো
    0.44
    大全
    0.42
    選項
    0.42
    -_
    0.42
     opção
    0.41
     ነገር
    0.41
     opções
    0.40
    㗊
    0.40
    POSITIVE LOGITS
     Sure
    0.37
    短短
    0.36
     el
    0.36
    Sure
    0.36
     Damn
    0.35
     strtok
    0.35
    <strong>
    0.34
    ël
    0.34
    機会
    0.34
    natives
    0.33
    Act Density 0.000%

    No Known Activations