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

    Neuronpedia

    INDEX
    Explanations

    month and day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ειτουργ
    0.64
    òria
    0.60
    第四
    0.57
    㣩
    0.57
     мотор
    0.56
    নীতিক
    0.56
    ၼ်
    0.55
    toolkit
    0.55
    äsident
    0.55
    opération
    0.54
    POSITIVE LOGITS
     |
    0.67
     alternatives
    0.58
     alternative
    0.54
     "
    0.51
     ten
    0.51
     Sri
    0.51
    0.51
     days
    0.50
     investment
    0.50
    ↵↵
    0.48
    Act Density 0.000%

    No Known Activations