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

    Neuronpedia

    INDEX
    Explanations

    lettuce turn over a new leaf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Principles
    0.44
    Component
    0.39
    逶
    0.38
    ће
    0.38
    उन्
    0.37
    یا
    0.37
    बॉलीवुड
    0.37
    プリン
    0.37
     चव्हाण
    0.37
    मेरे
    0.36
    POSITIVE LOGITS
     besten
    0.39
     finish
    0.39
     chút
    0.37
    fs
    0.37
    iasi
    0.36
     plato
    0.36
     beware
    0.36
     finishing
    0.36
     vl
    0.35
     LX
    0.35
    Act Density 0.001%

    No Known Activations