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

    Neuronpedia

    INDEX
    Explanations

    baked potato preparation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    0.99
    ী
    0.81
    ة
    0.71
    い
    0.70
    лото
    0.68
    0
    0.65
    ре
    0.62
    你
    0.61
    DIS
    0.61
    ร
    0.59
    POSITIVE LOGITS
     déprimées
    0.66
     रीजनिंग
    0.64
    <unused1031>
    0.64
    yatiti
    0.61
    pellier
    0.61
    <unused420>
    0.61
     Predicted
    0.60
     Have
    0.59
     senators
    0.59
     ESG
    0.59
    Act Density 0.004%

    No Known Activations