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

    Neuronpedia

    INDEX
    Explanations

    surprisingly diverse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आइक
    0.46
    oauth
    0.45
    Generic
    0.43
     atti
    0.43
    ule
    0.43
     ajuste
    0.42
    प्लेक्स
    0.42
    eosin
    0.42
    olen
    0.42
     ajustes
    0.42
    POSITIVE LOGITS
     PROJECTS
    0.44
     SA
    0.43
     NSW
    0.43
     Tugas
    0.43
     ČR
    0.42
     Cinema
    0.42
     LABOR
    0.42
     Targets
    0.41
     casinos
    0.40
     SURFACE
    0.40
    Act Density 0.012%

    No Known Activations