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

    Neuronpedia

    INDEX
    Explanations

    Mood states and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     равномер
    0.47
    War
    0.42
    тном
    0.41
    изо
    0.40
     тоже
    0.40
     waitFor
    0.40
     реали
    0.38
    áli
    0.38
     избе
    0.38
    真的
    0.37
    POSITIVE LOGITS
     titulo
    0.47
     instala
    0.45
     titul
    0.45
    ftp
    0.45
     Coleoptera
    0.44
    fia
    0.43
    criptors
    0.43
    Connections
    0.43
    偌
    0.43
    電源
    0.42
    Act Density 0.000%

    No Known Activations