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

    Neuronpedia

    INDEX
    Explanations

    states of being or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     souvent
    0.49
     europe
    0.47
     biomedical
    0.47
     européen
    0.47
     european
    0.46
     biot
    0.46
     depolarization
    0.46
     intranet
    0.46
     somos
    0.45
     europea
    0.45
    POSITIVE LOGITS
     Спа
    0.45
    Спа
    0.44
    颜值
    0.44
    适应
    0.44
    stö
    0.44
    依旧
    0.44
     Immaculate
    0.43
     അദ്ദേ
    0.42
    他说
    0.42
     שהוא
    0.41
    Act Density 0.001%

    No Known Activations