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

    Neuronpedia

    INDEX
    Explanations

    defining terms and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pseudomonas
    0.81
    眹
    0.81
     Yuki
    0.80
     Eug
    0.78
     IAAF
    0.78
     Bangor
    0.74
     lupus
    0.73
     UNICEF
    0.73
     Yung
    0.73
     Harlem
    0.73
    POSITIVE LOGITS
    থানি
    0.77
     തയ്യാ
    0.70
    ০০
    0.69
    ور
    0.67
     delante
    0.66
    ene
    0.65
     руководителя
    0.64
     руководи
    0.63
     consideración
    0.63
    тье
    0.63
    Act Density 0.003%

    No Known Activations