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

    Neuronpedia

    INDEX
    Explanations

    **1. list item or section start**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }"),
    0.22
    াধ
    0.22
     वचन
    0.22
    ”).
    0.22
     청
    0.21
     soltanto
    0.21
     requête
    0.21
     solicitud
    0.21
    .").
    0.21
     request
    0.20
    POSITIVE LOGITS
    💪
    0.26
    しかし
    0.25
     💪
    0.25
     Hoyt
    0.24
    ☯
    0.24
     Birch
    0.23
     Hayley
    0.23
     शेट्टी
    0.23
    🧙
    0.23
    🪴
    0.23
    Act Density 0.058%

    No Known Activations