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

    Neuronpedia

    INDEX
    Explanations

    outdoor habitat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     introduces
    0.43
    ম্ভীর
    0.42
     introducción
    0.40
     detener
    0.40
     potrebbero
    0.40
     môžu
    0.40
     μπορούν
    0.39
     hidrat
    0.39
    ículos
    0.39
     podrían
    0.39
    POSITIVE LOGITS
    รั
    0.47
    想着
    0.43
     받고
    0.42
     XGB
    0.42
     disgraceful
    0.42
    ॔
    0.42
     Deleted
    0.42
     अजून
    0.42
    arkhand
    0.42
     XIA
    0.42
    Act Density 0.006%

    No Known Activations